© 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. 9244
    Prev
    Next
    INDEX
    Explanations

    separating lists

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

    parentheses, code blocks, 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
    सेन
    0.44
    ὠ
    0.41
    তো
    0.41
     RESON
    0.41
    স্থার
    0.41
    metaTag
    0.40
    आपके
    0.40
    粱
    0.40
    煅
    0.40
    TempBuffer
    0.40
    POSITIVE LOGITS
     checklists
    0.47
     gu
    0.39
     langs
    0.39
    ‑
    0.39
     phd
    0.38
     rund
    0.38
     cho
    0.38
     zero
    0.38
     tur
    0.38
     ea
    0.37
    Activations Density 0.000%

    No Known Activations