© 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. 218503
    Prev
    Next
    INDEX
    Explanations

    rotation, sided, shoulder, flame, visually

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

    mimicking, danger, bite

    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
    L
    0.54
    handlers
    0.51
    H
    0.50
    }\}$.
    0.48
    LD
    0.46
    controllers
    0.46
     exemptions
    0.46
    height
    0.44
    lots
    0.44
    ओ
    0.44
    POSITIVE LOGITS
     rotational
    0.53
    迩
    0.50
     rota
    0.47
    ftone
    0.46
    gunakan
    0.46
    acă
    0.46
     Roth
    0.45
     御
    0.44
     bric
    0.44
    wać
    0.43
    Activations Density 0.002%

    No Known Activations