© 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. 109658
    Prev
    Next
    INDEX
    Explanations

    long time or period

    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
     PIP
    -0.81
    zapatilla
    -0.80
    Thiết
    -0.79
    ✃
    -0.76
    レトロ
    -0.76
    otros
    -0.76
     encontrados
    -0.75
     інші
    -0.75
    Huile
    -0.75
    jekk
    -0.75
    POSITIVE LOGITS
     time
    1.13
    time
    0.96
     use
    0.86
    vor
    0.81
    改
    0.80
     endometri
    0.79
    ૂ
    0.79
     service
    0.77
    using
    0.76
     using
    0.75
    Activations Density 0.016%

    No Known Activations