© 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. 41067
    Prev
    Next
    INDEX
    Explanations

    specific types of details

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

    brand names, origins, or rankings

    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
    -
    0.59
    OS
    0.53
    6
    0.53
    IO
    0.50
    އ
    0.50
    वे
    0.50
    CJK
    0.49
    olon
    0.49
    (
    0.49
    新
    0.47
    POSITIVE LOGITS
     જગ્યા
    0.49
    colorPrimary
    0.49
     நிலை
    0.47
     வண்ணப்பூச்சு
    0.46
     สถาน
    0.46
     लिहि
    0.46
     બિ
    0.45
     અત
    0.45
     सेल्फ
    0.44
     detalhes
    0.44
    Activations Density 0.000%

    No Known Activations