© 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. 112060
    Prev
    Next
    INDEX
    Explanations

    to contact

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

    AI understanding and reasoning

    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
    绣
    0.46
     Zijn
    0.46
     Heather
    0.44
     Ary
    0.44
    িশালী
    0.43
     corrupted
    0.43
     Rigid
    0.43
    bulldozer
    0.43
     Enzymes
    0.43
    этому
    0.43
    POSITIVE LOGITS
    </h1>
    0.47
    يكون
    0.47
    تمل
    0.47
     parad
    0.45
     china
    0.45
    amanam
    0.45
    אה
    0.42
    在北京
    0.42
    usic
    0.41
     चीन
    0.41
    Activations Density 0.000%

    No Known Activations