© 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. 242758
    Prev
    Next
    INDEX
    Explanations

    realizing ideas

    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
    h
    0.50
    u
    0.48
    uvat
    0.46
     igualmente
    0.45
    oju
    0.44
     человеку
    0.44
    deki
    0.44
     Kowloon
    0.44
    col
    0.43
    based
    0.43
    POSITIVE LOGITS
    TrackAngle
    0.57
    Bechyné
    0.46
    FileNotFound
    0.46
    грама
    0.45
     camino
    0.44
     conn
    0.43
     ቦ
    0.43
    ี
    0.43
     заре
    0.42
     wedding
    0.42
    Activations Density 0.000%

    No Known Activations