© 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. 185180
    Prev
    Next
    INDEX
    Explanations

    triggers, closes, President, involved, original, presence, wondering

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

    framework, problem, Miranda, Search, affects

    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
    Negative Logits
     देम
    0.50
     ABOUT
    0.49
    )].
    0.47
     DURING
    0.45
     तिथि
    0.45
     ].
    0.45
     FINANCE
    0.45
     맞아
    0.44
     MANAGEMENT
    0.44
     CRE
    0.44
    POSITIVE LOGITS
    är
    0.59
    asp
    0.56
    optical
    0.55
    aps
    0.54
    opez
    0.54
    order
    0.53
    au
    0.52
    arter
    0.51
    с
    0.50
    ang
    0.49
    Activations Density 0.000%

    No Known Activations