© 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. 166028
    Prev
    Next
    INDEX
    Explanations

    hour drive

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

    Greetings, technical terms, foreign words

    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
    getFocusAreas
    0.52
    jsonObject
    0.49
    radioButton
    0.48
     ویر
    0.48
     حکمت
    0.47
    )`;
    0.47
     بُک
    0.46
    蔦
    0.46
    jera
    0.46
     кандида
    0.45
    POSITIVE LOGITS
    -
    0.61
    0.59
     A
    0.50
     morphology
    0.45
      
    0.45
    ENTIAL
    0.42
     apreciar
    0.42
    Dev
    0.42
     Unified
    0.42
     appreciation
    0.42
    Activations Density 0.000%

    No Known Activations