© 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. 101967
    Prev
    Next
    INDEX
    Explanations

    star, witness, father, school, left, allowed

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

    associated with explanation

    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
    បន្ថែម
    0.41
    pe
    0.40
    ท้าย
    0.40
     ราคา
    0.40
    </b>
    0.39
    មើល
    0.39
     价
    0.39
    $,
    0.39
    hardening
    0.39
    thick
    0.38
    POSITIVE LOGITS
    લ્ડ
    0.51
     abd
    0.50
     लटका
    0.49
     causation
    0.47
     scienza
    0.47
     construe
    0.47
     eukary
    0.46
     Кай
    0.46
     chino
    0.45
     Бей
    0.45
    Activations Density 0.001%

    No Known Activations