© 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. 119153
    Prev
    Next
    INDEX
    Explanations

    Superficial, length, Q:

    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
     varargin
    -0.88
    ͒
    -0.72
     बाल
    -0.71
     Bahía
    -0.71
     possesses
    -0.70
     useRouter
    -0.70
     réus
    -0.69
     citrate
    -0.69
     βιβ
    -0.68
    ですか
    -0.68
    POSITIVE LOGITS
    干部
    0.77
     tasting
    0.77
    hahn
    0.75
     repuesto
    0.74
    ाप्त
    0.73
    łucha
    0.73
    ǚ
    0.73
    ificance
    0.73
    Cocktail
    0.73
     usta
    0.72
    Activations Density 0.002%

    No Known Activations