© 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. 10134
    Prev
    Next
    INDEX
    Explanations

    **

    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
    רים
    0.80
     Fortress
    0.80
    idum
    0.79
    {
    0.78
    lar
    0.78
     pev
    0.76
    ეს
    0.75
    })}$
    0.74
    ار
    0.73
    rong
    0.71
    POSITIVE LOGITS
     queremos
    1.12
     хотел
    0.93
     хотите
    0.92
     aussch
    0.84
     хочется
    0.84
     клиентов
    0.81
     струк
    0.80
     хотим
    0.80
     Straf
    0.80
    ारे
    0.80
    Activations Density 0.000%

    No Known Activations