© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5110
    Prev
    Next
    INDEX
    Explanations

    services, crash, techniques, dedicated, DNA(Looking at `MAX_ACTIVATING_TOKENS`: `services`, `crash`, `ctx` (related to context or SSL context), `techniques`, `dedicated`, `DNA`. These seem to point to technical or biological terms.`TOKENS_AFTER_MAX_ACTIVATING_TOKEN`: `Delay`, `online`, `.`, `,`, `to`, `):`. These follow some of the activating tokens like 'able' or '0'.services or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ین
    0.89
    кл
    0.85
    福
    0.84
    سم
    0.83
    ふ
    0.83
    ຟ
    0.83
    ದ
    0.82
    جا
    0.80
    ຕະ
    0.80
    tarif
    0.80
    POSITIVE LOGITS
    which
    0.78
    {
    0.78
    ).
    0.76
    k
    0.75
    ly
    0.75
    )
    0.75
    =
    0.73
     Vasily
    0.73
    mono
    0.73
     uma
    0.72
    Activations Density 0.000%

    No Known Activations