© 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. 180400
    Prev
    Next
    INDEX
    Explanations

    activities and events

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

    energy, colorful, fairly, immense, rebuilding, assume, GPT

    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
    empê
    0.49
     scammers
    0.49
    Jangan
    0.49
    َيْ
    0.47
    賺
    0.47
     úspě
    0.46
    금을
    0.45
     destined
    0.44
     popolo
    0.44
     Zahlung
    0.43
    POSITIVE LOGITS
    formed
    0.48
    ar
    0.46
    ap
    0.46
     Workspace
    0.42
    i
    0.42
    RI
    0.41
    x
    0.41
    本身的
    0.40
    au
    0.40
    recent
    0.39
    Activations Density 0.000%

    No Known Activations