© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81895
    Prev
    Next
    INDEX
    Explanations

    evaluating personality or physical action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     лежа
    0.40
     пропуска
    0.39
    checkBox
    0.37
    从未
    0.37
    Quit
    0.36
    几
    0.36
    Kings
    0.36
    kings
    0.36
    挡
    0.36
    我们也
    0.36
    POSITIVE LOGITS
    䛶
    0.56
    sete
    0.54
    ್ಟ
    0.54
     Belize
    0.53
    Ꮞ
    0.52
    یف
    0.51
     belge
    0.51
    楾
    0.50
     SCI
    0.50
     gamme
    0.50
    Activations Density 0.000%

    No Known Activations