© 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. 248152
    Prev
    Next
    INDEX
    Explanations

    following punctuation or phrases

    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
    ل
    0.54
     Gölü
    0.47
    otom
    0.45
    பர
    0.45
    স্থানীয়
    0.45
    మాట
    0.45
    ॉक्स
    0.44
    ल
    0.44
    ólicos
    0.43
     Aank
    0.43
    POSITIVE LOGITS
     것이다
    0.44
     하여
    0.43
     CONTRIBUT
    0.43
    녕
    0.43
    wsgi
    0.42
    正是
    0.41
    (\{
    0.41
     또한
    0.41
    )$;
    0.41
     갔
    0.41
    Activations Density 0.001%

    No Known Activations