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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76807
    Prev
    Next
    INDEX
    Explanations

    fishing and hunting

    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
    磁盘
    -0.85
    functional
    -0.82
    और
    -0.80
    behandling
    -0.76
     पढ़
    -0.75
     Audiodateien
    -0.75
     integrated
    -0.75
    ριο
    -0.74
     psicológica
    -0.74
    服务的
    -0.73
    POSITIVE LOGITS
     venues
    1.15
     venue
    1.12
    Venue
    0.93
    VENUE
    0.88
     syndicate
    0.88
     baili
    0.86
    🏟
    0.85
     peg
    0.84
     session
    0.84
     [:
    0.84
    Activations Density 0.006%

    No Known Activations