© 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. 144741
    Prev
    Next
    INDEX
    Explanations

    numbers and finance

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

    Tidal Locking, GTAW, Hanoi `destination`, `i++`, clockwise

    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
    dDevice
    0.49
    INF
    0.45
    throwing
    0.45
    uzzy
    0.44
    ্যালি
    0.43
    AST
    0.42
    AUT
    0.42
    干
    0.42
    computation
    0.42
    y
    0.42
    POSITIVE LOGITS
     unilateral
    0.59
     cheque
    0.56
     regl
    0.55
     venda
    0.54
     acaba
    0.53
     finit
    0.53
     Christendom
    0.53
     ridiculous
    0.53
     liquidate
    0.52
     stip
    0.51
    Activations Density 0.001%

    No Known Activations