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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118593
    Prev
    Next
    INDEX
    Explanations

    available at online sources

    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
    ESTADO
    -0.94
    Demografie
    -0.91
     flota
    -0.89
     tē
    -0.87
    źć
    -0.85
     شهرهای
    -0.84
    ATEN
    -0.84
    ifts
    -0.81
    🦝
    -0.80
     piscina
    -0.79
    POSITIVE LOGITS
     at
    2.08
     online
    1.23
    https
    1.13
     available
    1.13
    http
    1.12
     http
    1.11
     URL
    1.10
     from
    1.06
    URL
    1.00
     https
    0.99
    Activations Density 0.013%

    No Known Activations