© 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. 245363
    Prev
    Next
    INDEX
    Explanations

    league, extinction, girl, allocations

    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
     và
    0.56
     and
    0.53
     but
    0.48
     similaires
    0.45
     k
    0.44
     oraz
    0.44
     yang
    0.43
     viral
    0.43
     influencers
    0.43
     şi
    0.43
    POSITIVE LOGITS
    ЕР
    0.50
    пе
    0.49
    лай
    0.49
    новой
    0.46
    אי
    0.45
    이드
    0.45
    네요
    0.45
    几年
    0.45
    옛
    0.44
    hopefully
    0.44
    Activations Density 0.013%

    No Known Activations