© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39112
    Prev
    Next
    INDEX
    Explanations

    company and its actions

    np_acts-logits-general · gemini-2.5-flash-lite

    company name, policies, wide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ם
    0.96
    лна
    0.92
    ف
    0.91
     библиоте
    0.91
    க்
    0.89
     conclu
    0.89
    。
    0.87
     храм
    0.86
    ں
    0.86
    мимо
    0.85
    POSITIVE LOGITS
    g
    1.37
    t
    1.30
    1
    1.20
    w
    1.16
    A
    1.05
    Company
    1.05
    ing
    1.03
    v
    1.02
    es
    1.00
    b
    0.97
    Activations Density 0.061%

    No Known Activations