© 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. 52112
    Prev
    Next
    INDEX
    Explanations

    roman numerals with comma

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

    longer distances involved

    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
    UMI
    0.58
    NumConst
    0.46
    TS
    0.45
    Sensor
    0.45
    Dot
    0.45
    (())
    0.44
    மைக்
    0.44
    )_
    0.44
    ﺕ
    0.44
    Operator
    0.43
    POSITIVE LOGITS
     socialism
    0.54
    㱛
    0.48
     शैक्षिक
    0.47
     socialist
    0.46
     पढ़े
    0.45
    撗
    0.45
     మరియు
    0.45
     వార్
    0.45
     राजनीतिक
    0.44
     फ़
    0.44
    Activations Density 0.000%

    No Known Activations