© 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. 96153
    Prev
    Next
    INDEX
    Explanations

    specific nouns and adjectives

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

    explains what it is

    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
    addContainerGap
    0.42
    Courtesy
    0.42
    DAVID
    0.41
    序号
    0.41
     کرمان
    0.41
    {"
    0.41
    是一
    0.41
    在一
    0.40
     Connector
    0.40
     активно
    0.39
    POSITIVE LOGITS
     lexic
    0.50
    ਾਇ
    0.46
     caches
    0.44
     cohé
    0.44
     equivari
    0.43
    トート
    0.43
     quién
    0.43
     generalised
    0.43
     donc
    0.43
    ೇಖ
    0.43
    Activations Density 0.000%

    No Known Activations