© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205324
    Prev
    Next
    INDEX
    Explanations

    pick your

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

    issues, errors, or mistakes

    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
    Negative Logits
    C
    0.46
    A
    0.46
    E
    0.45
    ER
    0.44
    VIDIA
    0.44
    INES
    0.43
    内部
    0.43
     UI
    0.43
    っぽ
    0.43
    Friends
    0.42
    POSITIVE LOGITS
     evidentemente
    0.54
     세제곱
    0.53
     ხელ
    0.52
     transdu
    0.52
    긋
    0.51
     quenched
    0.50
    穰
    0.50
     μπορεί
    0.50
     superflu
    0.49
     производи
    0.48
    Activations Density 0.000%

    No Known Activations