© 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. 166493
    Prev
    Next
    INDEX
    Explanations

    appear sound, embodiments of

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

    Maharaja, Predictive Policing, Brain

    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
    ก็จะ
    0.49
     envis
    0.47
    »).
    0.45
    เครื่อง
    0.44
     envisaged
    0.43
     showering
    0.43
    >.
    0.43
     энерго
    0.42
    ى
    0.42
    คืน
    0.41
    POSITIVE LOGITS
     Maharaja
    0.50
    Plain
    0.49
    Z
    0.49
     महाराजा
    0.49
    W
    0.49
     plain
    0.47
     高校
    0.47
     部分
    0.47
    Ō
    0.47
     मैदान
    0.46
    Activations Density 0.000%

    No Known Activations