© 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. 180756
    Prev
    Next
    INDEX
    Explanations

    consolidate inbound, beneficially

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

    Perception vs. Reality

    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
    ?
    0.46
    I
    0.45
    D
    0.44
    s
    0.43
     DIRECTION
    0.43
    la
    0.42
    inko
    0.42
    \
    0.42
    ?”
    0.41
     Direction
    0.41
    POSITIVE LOGITS
     شك
    0.53
     مغ
    0.50
     Moc
    0.50
     erwarten
    0.49
     семья
    0.48
    ທາງ
    0.48
     هيك
    0.48
     resistant
    0.47
     conocimientos
    0.47
     fieldContext
    0.47
    Activations Density 0.000%

    No Known Activations