© 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. 163900
    Prev
    Next
    INDEX
    Explanations

    shoulder painsoftware problemsdisc spec

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

    Elden Ring, caption options, Transport Layer

    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
     SITE
    0.54
     GAME
    0.51
    齋
    0.50
    看到
    0.50
     при
    0.49
     thấy
    0.49
    די
    0.48
     agradecer
    0.48
    マーケ
    0.48
    dé
    0.48
    POSITIVE LOGITS
    rowadz
    0.50
    foil
    0.50
    receipt
    0.47
    Butyl
    0.44
     characterised
    0.44
     لیکن
    0.44
    =[-
    0.44
    oping
    0.43
    +"
    0.42
    vertex
    0.42
    Activations Density 0.000%

    No Known Activations