© 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. 159121
    Prev
    Next
    INDEX
    Explanations

    condo, notice, important, residential, scans

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

    so fantastic

    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
     Origin
    0.48
     Fédération
    0.47
     M
    0.47
    (
    0.47
    ll
    0.46
    VIC
    0.45
    YS
    0.45
    SM
    0.44
     Hatch
    0.44
     Mohd
    0.44
    POSITIVE LOGITS
    ాలని
    0.49
    тием
    0.48
    اسية
    0.48
    濤
    0.46
    キン
    0.46
    wonderful
    0.43
    sinatra
    0.43
    cookieParser
    0.42
    siswa
    0.42
    涛
    0.41
    Activations Density 0.004%

    No Known Activations