© 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. 178095
    Prev
    Next
    INDEX
    Explanations

    vector, November, eye, taped

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

    preventing negative outcomes

    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
    mathbf
    0.49
     phrasing
    0.49
    માં
    0.48
    Preface
    0.48
    ल
    0.46
     isotherms
    0.46
    ھا
    0.45
     سا
    0.45
    ம்
    0.44
     ব্যাপকভাবে
    0.44
    POSITIVE LOGITS
    naval
    0.45
    夺
    0.44
    वर्स
    0.43
    ivit
    0.43
     ích
    0.43
     allí
    0.42
     mentored
    0.42
     navegación
    0.41
    zę
    0.41
    lok
    0.40
    Activations Density 0.000%

    No Known Activations