© 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. 145345
    Prev
    Next
    INDEX
    Explanations

    according to, other languages

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

    different ways of stating something

    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
     Gouver
    0.45
    ব্রি
    0.45
    샤
    0.44
     interrom
    0.43
     OUTER
    0.43
    まるで
    0.43
     whe
    0.42
     REACTOR
    0.42
     faudra
    0.41
    ジャー
    0.41
    POSITIVE LOGITS
     enligt
    0.53
     volgens
    0.50
    4
    0.49
     jiné
    0.47
    agility
    0.47
     according
    0.47
    qt
    0.47
     being
    0.46
    ক্তির
    0.45
    cs
    0.44
    Activations Density 0.000%

    No Known Activations