© 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. 150490
    Prev
    Next
    INDEX
    Explanations

    talents were, Movie that, table-, marker placement

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

    descriptive nouns and adjectives

    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
    ﻬ
    0.48
     limitado
    0.48
    нения
    0.47
     pinturas
    0.47
     यदि
    0.46
     उत्तर
    0.46
     pastries
    0.46
     אשר
    0.45
    也不会
    0.45
     karne
    0.44
    POSITIVE LOGITS
     Vienna
    0.47
    वर्ड
    0.46
    周
    0.46
    </em>
    0.45
     Volleyball
    0.45
    Question
    0.45
     Austria
    0.44
     dichiar
    0.44
     jum
    0.43
     Jaeger
    0.43
    Activations Density 0.001%

    No Known Activations