© 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. 16760
    Prev
    Next
    INDEX
    Explanations

    concepts followed by context

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

    hypothetical situations and changes

    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
    לת
    0.56
    ש
    0.54
    ל
    0.52
     અને
    0.52
    もしくは
    0.52
    ล์
    0.51
     ಮತ್ತು
    0.50
    ק
    0.50
    ון
    0.50
    מי
    0.50
    POSITIVE LOGITS
     postulated
    0.46
     hypothesized
    0.43
     dyads
    0.42
     analogous
    0.42
     killed
    0.41
     الذين
    0.41
     newly
    0.40
     cuyos
    0.40
     carelessly
    0.40
     whose
    0.40
    Activations Density 0.001%

    No Known Activations