© 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. 12823
    Prev
    Next
    INDEX
    Explanations

    appeal

    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
    ка
    2.27
    ください
    2.22
    ם
    2.20
    ки
    2.14
    ної
    2.09
    いた
    2.06
    sı
    2.02
    ного
    1.99
    да
    1.94
    singer
    1.93
    POSITIVE LOGITS
    끔
    1.60
     schle
    1.53
     viac
    1.51
     Comme
    1.49
     Coelho
    1.45
     tangents
    1.44
     Clements
    1.43
     Callable
    1.43
     Characteristics
    1.39
     Ss
    1.39
    Activations Density 0.032%

    No Known Activations