© 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. 46156
    Prev
    Next
    INDEX
    Explanations

    "Introduction", "Developing", "Finally"

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

    concepts and definitions

    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
     Equally
    0.46
     Paul
    0.46
     Amsterdam
    0.44
     F
    0.42
     Women
    0.42
     Starring
    0.41
     Foley
    0.41
     Home
    0.41
     starred
    0.40
     Loving
    0.40
    POSITIVE LOGITS
    seudo
    0.43
    incipal
    0.42
     言
    0.42
    ousal
    0.42
    '،
    0.42
    versation
    0.41
    來說
    0.41
     interrelated
    0.40
    看待
    0.39
    rochemical
    0.39
    Activations Density 0.002%

    No Known Activations