© 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. 106563
    Prev
    Next
    INDEX
    Explanations

    another, Aggregation, daily, AGAIN

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

    numbered lists and parsing

    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
     underpinned
    0.54
     variances
    0.50
     dates
    0.49
    Კ
    0.49
     frescoes
    0.47
     blackened
    0.47
     insistent
    0.47
     sobriety
    0.46
     personable
    0.46
     fanatic
    0.46
    POSITIVE LOGITS
    ס
    0.55
    ג
    0.51
     Parse
    0.50
     Parsing
    0.49
    Another
    0.48
    Filtering
    0.48
    Former
    0.48
    Designed
    0.48
    Otra
    0.47
    Autres
    0.47
    Activations Density 0.000%

    No Known Activations