© 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. 150697
    Prev
    Next
    INDEX
    Explanations

    pandas as pd

    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
    ذ
    0.55
    pt
    0.48
    b
    0.46
    sal
    0.45
    nten
    0.45
     जहां
    0.45
    zal
    0.43
    એ
    0.43
    the
    0.43
    eb
    0.42
    POSITIVE LOGITS
    Riemann
    0.52
    เที่ยว
    0.51
     fattori
    0.49
     sexe
    0.49
    行情
    0.48
     ragione
    0.48
    季节
    0.48
    绾
    0.47
    蠡
    0.47
     racconta
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.