© 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. 153695
    Prev
    Next
    INDEX
    Explanations

    temporal, business, and account details

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

    Convolution, prices, topic

    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
    槐
    0.48
    ઠા
    0.47
    તિ
    0.46
    𝗩
    0.46
     बच्ची
    0.45
    곽
    0.45
     assent
    0.44
    ásticos
    0.44
    enio
    0.44
    纭
    0.43
    POSITIVE LOGITS
     perspekt
    0.48
     perspective
    0.46
     zeigt
    0.46
     tulee
    0.46
     dieses
    0.45
     symmetric
    0.45
     spekt
    0.44
     reentry
    0.44
     symmetrical
    0.43
     mellem
    0.43
    Activations Density 0.000%

    No Known Activations