© 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. 206012
    Prev
    Next
    INDEX
    Explanations

    how else would

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

    harmful fantasies and real-world consequences

    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
     мнение
    0.55
     míst
    0.54
    㑅
    0.54
     puente
    0.52
    ен
    0.52
    ём
    0.50
    䂧
    0.50
    䅞
    0.50
     ダイ
    0.49
     úgy
    0.49
    POSITIVE LOGITS
    Berkeley
    0.50
    Maryland
    0.47
    Donald
    0.46
     perhaps
    0.46
     University
    0.46
    0.43
    University
    0.43
    perhaps
    0.42
    Century
    0.42
    East
    0.42
    Activations Density 0.000%

    No Known Activations