© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113771
    Prev
    Next
    INDEX
    Explanations

    bars and nightlife

    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_10/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
     was
    -2.94
    
    -2.83
    却又
    -2.77
     We
    -2.58
    姈
    -2.53
    ᯾
    -2.50
     θα
    -2.39
     เรา
    -2.38
     唯美
    -2.36
    спомина
    -2.34
    POSITIVE LOGITS
    to
    3.25
    </strong>
    2.91
     If
    2.83
     alkoh
    2.81
     anderen
    2.81
     jabatan
    2.58
     pemilik
    2.55
     keterangan
    2.53
    媖
    2.45
    )」
    2.42
    Activations Density 0.003%

    No Known Activations