© 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. 242646
    Prev
    Next
    INDEX
    Explanations

    alternative options

    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
     ouvir
    0.52
     ـ
    0.52
    arrive
    0.48
     Februar
    0.47
     佐
    0.47
     gewüns
    0.47
     مِنْ
    0.47
     व
    0.46
     الإص
    0.46
    <0xAF>
    0.46
    POSITIVE LOGITS
    เวล
    0.46
     accumulator
    0.44
    ંદર
    0.44
    जबकि
    0.42
     piss
    0.42
    クロ
    0.41
     classics
    0.41
     metabolites
    0.41
     beings
    0.41
    endre
    0.40
    Activations Density 0.001%

    No Known Activations