© 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. 189354
    Prev
    Next
    INDEX
    Explanations

    file parts protected database version

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

    tailor to job description

    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
    ｱ
    0.52
     hermosa
    0.49
    א
    0.48
    9
    0.47
    аны
    0.47
    VAL
    0.46
    ೃಷ್ಣ
    0.46
     люблю
    0.46
    氈
    0.46
    ਿਲ
    0.45
    POSITIVE LOGITS
    解决方法
    0.54
     Nexon
    0.50
     unconsciously
    0.50
     horrifying
    0.50
     effektiv
    0.48
     mindless
    0.48
     umiejęt
    0.47
    Rightarrow
    0.47
     crippling
    0.47
     Chaotic
    0.46
    Activations Density 0.004%

    No Known Activations