Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11933
    Prev
    Next
    INDEX
    Explanations

    private keyword

    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_22/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
    着脸
    -1.05
    mische
    -1.02
    Nossa
    -1.00
    Apesar
    -1.00
    幹線
    -0.99
    Então
    -0.96
    Até
    -0.95
     endeavouring
    -0.95
    :……
    -0.94
    Mesmo
    -0.94
    POSITIVE LOGITS
     also
    1.48
     также
    1.18
     and
    0.98
     Also
    0.97
     também
    0.96
    kkk
    0.96
    。
    0.94
    damit
    0.93
    Nuorodos
    0.90
     vistazo
    0.90
    Activations Density 0.014%

    No Known Activations