© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60097
    Prev
    Next
    INDEX
    Explanations

    [noun] of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ródła
    -0.86
    For
    -0.82
    これを
    -0.82
    ちなみに
    -0.77
    鮪
    -0.76
    матика
    -0.76
    憩
    -0.75
     because
    -0.75
    鍵
    -0.74
    而在
    -0.73
    POSITIVE LOGITS
    Jeg
    0.85
    サミ
    0.82
     hoje
    0.77
    (!)
    0.77
     (+)
    0.76
    émie
    0.76
    ⍺
    0.76
     (!)
    0.76
    BEAM
    0.76
     Präsidenten
    0.75
    Activations Density 0.331%

    No Known Activations