© 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. 175940
    Prev
    Next
    INDEX
    Explanations

    growth segments

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

    innocence, date, technology, dramatic

    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
    debris
    0.55
     organizational
    0.46
    美人
    0.45
    PCS
    0.44
    in
    0.42
     debris
    0.42
    }=(
    0.42
    materials
    0.41
    VOA
    0.41
    ва
    0.41
    POSITIVE LOGITS
     Gérard
    0.54
     Enquiry
    0.54
     Bourgogne
    0.53
    🍖
    0.52
     pénétr
    0.50
     Gentleman
    0.50
    🍾
    0.49
     peut
    0.48
     ダイニング
    0.48
     tatou
    0.48
    Activations Density 0.000%

    No Known Activations