© 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. 67004
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

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

    numbers after punctuation

    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
    as
    0.52
    3
    0.49
    x
    0.48
    8
    0.46
    9
    0.45
    4
    0.45
    +
    0.44
    -
    0.44
    6
    0.43
    1
    0.43
    POSITIVE LOGITS
     ትንሽ
    0.44
    साइटी
    0.42
    ейчас
    0.42
     గురించి
    0.42
     ያስፈል
    0.42
     తయారు
    0.40
     النرويج
    0.40
    ponses
    0.39
     gehört
    0.39
     رولی
    0.39
    Activations Density 0.008%

    No Known Activations