© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12902
    Prev
    Next
    INDEX
    Explanations

    time durations (years, nights, cycles)

    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
    ヴィ
    0.53
    विता
    0.50
     ಇಂಡ
    0.47
    вань
    0.46
    desPort
    0.45
    Ὀ
    0.45
     ಕ್ಷೇತ್ರದಲ್ಲಿ
    0.45
    شان
    0.45
     영역
    0.45
     crucifixion
    0.44
    POSITIVE LOGITS
     (
    0.49
     así
    0.45
    ated
    0.44
     with
    0.42
     Ahora
    0.42
     Eisen
    0.42
     &
    0.41
     Plato
    0.41
     Wagner
    0.41
     Carte
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.