© 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. 221971
    Prev
    Next
    INDEX
    Explanations

    claims priority

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

    points away, become cheaper, pronunciations

    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
     וש
    0.50
    Vecchio
    0.48
     نمی
    0.48
    ichung
    0.48
    flug
    0.47
     黑
    0.46
    த்
    0.46
    Ohio
    0.45
     ύ
    0.45
    !“
    0.45
    POSITIVE LOGITS
    ﺱ
    0.53
     skupiny
    0.47
    c
    0.46
    cjs
    0.44
    ©
    0.44
     personnes
    0.43
    (",",
    0.43
    辶
    0.42
     &.
    0.42
     piensan
    0.42
    Activations Density 0.000%

    No Known Activations