© 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. 136520
    Prev
    Next
    INDEX
    Explanations

    phrases about goods and services

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

    settlement finality, last name, storytelling

    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
     Namen
    0.52
    '
    0.47
    看到
    0.44
     Miniature
    0.41
     Ire
    0.40
     dbo
    0.40
     Polite
    0.39
     Print
    0.39
     defense
    0.39
     Vern
    0.39
    POSITIVE LOGITS
    ್ಟ
    0.55
     ຫຼື
    0.50
    jangan
    0.49
     unstable
    0.49
    ड़ों
    0.47
    جہ
    0.46
    કિસ્
    0.46
     갈
    0.45
    Edad
    0.45
    onka
    0.45
    Activations Density 0.003%

    No Known Activations