© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 182186
    Prev
    Next
    INDEX
    Explanations

    sharing entries or other tips

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

    relies on investigation; harmful tropes; potential

    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
    م
    0.55
    "
    0.54
    "،
    0.52
    "@
    0.45
    :"
    0.43
    वतात
    0.43
     مت
    0.43
    مس
    0.42
    وش
    0.42
     త
    0.42
    POSITIVE LOGITS
     saurait
    0.47
    RPG
    0.45
    LEN
    0.44
    応援
    0.43
     viewer
    0.42
     prudence
    0.41
     Ita
    0.41
     脚
    0.41
    readme
    0.41
     solvable
    0.41
    Activations Density 0.001%

    No Known Activations