© 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. 59147
    Prev
    Next
    INDEX
    Explanations

    authors names and titles

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

    even when unexpected

    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
    t
    0.63
     seti
    0.59
     han
    0.47
     brug
    0.47
     roma
    0.46
     vred
    0.46
     robert
    0.45
     proje
    0.45
     informazioni
    0.45
     opere
    0.45
    POSITIVE LOGITS
     Unemployment
    0.47
     Hazardous
    0.45
     Aufenthalt
    0.45
     Induced
    0.44
    ೇವೆ
    0.44
    >×</
    0.43
    ails
    0.43
    }=
    0.43
    上半年
    0.43
     летом
    0.43
    Activations Density 0.000%

    No Known Activations