© 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. 190831
    Prev
    Next
    INDEX
    Explanations

    reminder, loans, times, circuits, restoration, business

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

    familiar, generally, normally, defined, category

    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
    iments
    0.52
     unauthorized
    0.49
    hyth
    0.47
     exclusive
    0.46
    rud
    0.46
    ente
    0.45
    ਯ
    0.45
    あなたは
    0.45
    就业
    0.45
    გრ
    0.44
    POSITIVE LOGITS
     cristianos
    0.55
    ÂN
    0.48
     gaye
    0.48
     thefe
    0.47
     dSample
    0.46
    📩
    0.46
     Donate
    0.46
     Kirst
    0.45
     vesc
    0.45
     Iterate
    0.45
    Activations Density 0.001%

    No Known Activations