© 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. 31-GEMMASCOPE-2-RES-16K
    7. 645
    Prev
    Next
    INDEX
    Explanations

    speech verbs followed by punctuation

    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_31_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
     says
    0.66
    :
    0.63
     Says
    0.59
     säger
    0.59
    Says
    0.58
    说
    0.57
     decir
    0.57
    says
    0.56
     said
    0.55
    你说
    0.54
    POSITIVE LOGITS
    ,<
    0.60
    。「
    0.56
    .,
    0.55
    。“
    0.54
     بعد
    0.53
    。
    0.53
    ,.
    0.52
    .$,
    0.52
    ،
    0.52
    .
    0.51
    Activations Density 0.046%

    No Known Activations