© 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. 60440
    Prev
    Next
    INDEX
    Explanations

    project group want

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

    rhythmic sweep or pulse

    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
     commutes
    0.45
    IN
    0.43
    喜欢的
    0.43
    prefs
    0.42
    ை
    0.42
    翌
    0.42
     it
    0.41
    AS
    0.41
    SB
    0.41
     terci
    0.41
    POSITIVE LOGITS
     Sicherheit
    0.60
     Surety
    0.48
     యుద్ధ
    0.47
     perjanjian
    0.45
     법
    0.44
     技術
    0.44
     Milliarden
    0.44
     Beschreibung
    0.43
     Vertrag
    0.43
     حرب
    0.43
    Activations Density 0.000%

    No Known Activations