© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 167960
    Prev
    Next
    INDEX
    Explanations

    per person

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

    from an / from multiple

    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
    -
    0.48
    ty
    0.45
    }]\
    0.45
     ప్రభుత్వ
    0.44
     खुलने
    0.42
     nhàng
    0.41
     defunct
    0.40
    ensioni
    0.40
    t
    0.40
    伌
    0.40
    POSITIVE LOGITS
    ின்றனர்
    0.52
    ジオ
    0.48
    処理
    0.47
     νέ
    0.46
    Jis
    0.46
    辻
    0.45
    newState
    0.44
     と
    0.44
    ور
    0.43
     hoti
    0.43
    Activations Density 0.001%

    No Known Activations