© 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. 54987
    Prev
    Next
    INDEX
    Explanations

    sales, income, revenue

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

    consequences or harm

    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
    is
    0.52
     be
    0.48
     y
    0.48
    đ
    0.47
     Boxer
    0.47
    ard
    0.46
    OP
    0.46
    asp
    0.46
    faits
    0.45
    outi
    0.45
    POSITIVE LOGITS
    仩
    0.56
    朳
    0.52
    ايبي
    0.51
    㫧
    0.50
    ဈ
    0.49
    圿
    0.49
    豉
    0.49
     божомол
    0.48
    ريقيا
    0.48
    ᅧ
    0.48
    Activations Density 0.000%

    No Known Activations