© 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. 193919
    Prev
    Next
    INDEX
    Explanations

    various modifiers and nouns

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

    key terms in lists

    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
    oral
    0.49
    noh
    0.48
    ー
    0.46
    drug
    0.46
    guid
    0.46
    CHR
    0.46
    ahre
    0.45
    Bike
    0.44
    WAL
    0.44
    larger
    0.43
    POSITIVE LOGITS
     compless
    0.59
     rappresent
    0.53
     reprez
    0.50
     svil
    0.49
     felhasznál
    0.48
    怒
    0.48
     యువ
    0.48
     représent
    0.47
     reprezent
    0.47
     alınd
    0.47
    Activations Density 0.000%

    No Known Activations