© 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. 99856
    Prev
    Next
    INDEX
    Explanations

    weekly newsletter

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

    creating products

    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
     دي
    0.46
    aard
    0.45
    ಂಡ
    0.44
    ס
    0.44
     infl
    0.44
     indoor
    0.44
     ups
    0.44
    habt
    0.43
     indoors
    0.43
    인트
    0.43
    POSITIVE LOGITS
    Pur
    0.50
    ine
    0.49
     Progressives
    0.47
     विराजमान
    0.46
    tera
    0.46
    '}
    0.46
    platforms
    0.46
    ͠
    0.45
     विषय
    0.44
    esten
    0.44
    Activations Density 0.000%

    No Known Activations