© 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. 158936
    Prev
    Next
    INDEX
    Explanations

    organizers, previously, facsimile, moon, owe

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

    specific nouns and technical terms

    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
    asının
    0.52
    વાહી
    0.49
     پھی
    0.48
     vaik
    0.48
    rard
    0.48
     爱
    0.48
    ર્ડ
    0.48
    驯
    0.47
     වන
    0.47
    ्टर
    0.47
    POSITIVE LOGITS
    ax
    0.47
    DU
    0.46
    *
    0.45
    Δ
    0.45
    Mand
    0.44
    FF
    0.44
    VEL
    0.43
    Bx
    0.43
    DA
    0.43
    ೋ
    0.43
    Activations Density 0.000%

    No Known Activations