© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111626
    Prev
    Next
    INDEX
    Explanations

    terms and conditions, usage

    np_acts-logits-general · gemini-2.5-flash-lite

    asking about authors, bands, or clothes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🦟
    0.52
    วัด
    0.49
     วัด
    0.48
    MktCap
    0.48
    olique
    0.47
    Prothorax
    0.47
    stvu
    0.46
    ńcz
    0.45
     हिस्सा
    0.45
    corper
    0.45
    POSITIVE LOGITS
     e
    0.54
    獅
    0.53
     have
    0.47
     c
    0.45
     construe
    0.45
     HAS
    0.45
     sion
    0.45
     penal
    0.43
     stressed
    0.43
     t
    0.43
    Activations Density 0.000%

    No Known Activations