© 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. 9977
    Prev
    Next
    INDEX
    Explanations

    latex code blocks

    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
     personable
    1.45
     aidant
    1.19
     savvy
    1.16
     pyaar
    1.16
     pagamento
    1.16
    售后
    1.13
     distraught
    1.13
    揍
    1.13
     salespeople
    1.12
     employees
    1.10
    POSITIVE LOGITS
    ׳
    1.27
    ological
    1.27
    ({\
    1.22
    ри
    1.16
    1.13
    {\
    1.13
     происходит
    1.13
    id
    1.10
     מק
    1.09
    ans
    1.06
    Activations Density 0.004%

    No Known Activations