© 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. 106827
    Prev
    Next
    INDEX
    Explanations

    object, steel, document, kin

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

    cannot provide instructions

    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
     株
    0.48
     꿈
    0.47
     跳转
    0.47
     ство
    0.46
     बुरे
    0.46
    ǜ
    0.46
    股份
    0.44
     ẩn
    0.44
    𝕌
    0.44
    équation
    0.43
    POSITIVE LOGITS
     bombardment
    0.54
    т
    0.50
    Mes
    0.43
    gent
    0.43
     gadget
    0.43
     petri
    0.42
     playtime
    0.42
     plague
    0.41
     Familiar
    0.41
    Vet
    0.41
    Activations Density 0.000%

    No Known Activations