© 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. 33401
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    separators and numbers

    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
    \%).
    0.48
    orithm
    0.45
    abajo
    0.45
     শতাংশ
    0.44
    百分
    0.43
    িতি
    0.43
    เดือน
    0.43
    \%.
    0.42
    0.42
    াবল
    0.42
    POSITIVE LOGITS
     |
    0.52
     →
    0.46
     >>
    0.45
     东
    0.44
     >
    0.43
     東
    0.42
     [[
    0.42
     ›
    0.41
     ]]
    0.41
     ҳам
    0.40
    Activations Density 0.001%

    No Known Activations