© 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. 110621
    Prev
    Next
    INDEX
    Explanations

    Single property details

    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
     will
    -0.93
     株
    -0.79
     節
    -0.77
    ][:
    -0.73
     werden
    -0.73
    🤶
    -0.72
     Tenggara
    -0.72
     garansi
    -0.71
     yr
    -0.70
    ्ला
    -0.69
    POSITIVE LOGITS
     espaces
    0.82
    partida
    0.82
    iscus
    0.81
    INGER
    0.77
     DEEP
    0.77
     gardent
    0.76
    discussed
    0.76
    Dimensi
    0.76
    シャレ
    0.76
     profonde
    0.76
    Activations Density 0.002%

    No Known Activations