© 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. 95498
    Prev
    Next
    INDEX
    Explanations

    follow attitudes

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

    destroyed by Vogons

    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
    Ź
    0.54
    லாத
    0.50
    izat
    0.46
    ële
    0.46
    itectura
    0.46
    ٥
    0.45
    뚤
    0.45
    श्री
    0.45
    feliz
    0.45
     اصلی
    0.45
    POSITIVE LOGITS
     repudi
    0.53
     tax
    0.51
     conversions
    0.48
     ବ
    0.48
     CROSS
    0.48
     conversion
    0.47
    優惠
    0.46
     barbec
    0.46
     hypotheses
    0.46
     annuities
    0.46
    Activations Density 0.002%

    No Known Activations