© 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. 245444
    Prev
    Next
    INDEX
    Explanations

    formal and specific nouns

    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
     ня
    0.56
     общего
    0.55
     ذکر
    0.54
     хими
    0.54
     말
    0.53
     เศ
    0.52
     अर
    0.51
     त्व
    0.51
     उक्त
    0.51
     устрой
    0.50
    POSITIVE LOGITS
    Happy
    0.50
    是非
    0.46
    LEG
    0.46
    正式
    0.46
    রিদ
    0.44
    芜
    0.44
    HAPPY
    0.43
    Audit
    0.42
    初
    0.42
    緖
    0.42
    Activations Density 0.001%

    No Known Activations