© 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. 77362
    Prev
    Next
    INDEX
    Explanations

    Prophet Muhammad

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

    personal growth

    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
     risks
    0.47
     path
    0.47
     kV
    0.47
     ሃ
    0.46
     counties
    0.46
     risques
    0.46
     MCF
    0.46
     VESSELS
    0.45
     ідэ
    0.45
     CANADA
    0.44
    POSITIVE LOGITS
    น
    0.49
     Constru
    0.48
    Mood
    0.48
    ال
    0.46
    ックス
    0.46
     Mood
    0.45
    Essential
    0.45
    自動
    0.44
    釉
    0.44
    Basic
    0.44
    Activations Density 0.000%

    No Known Activations