© 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. 163293
    Prev
    Next
    INDEX
    Explanations

    describing states or outcomes

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

    foreign language words and code constructs

    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
    Ngày
    0.49
    美國
    0.47
    الث
    0.47
    aktoren
    0.46
    AB
    0.46
    Deux
    0.46
    戰
    0.45
     flott
    0.45
    6
    0.44
    abcd
    0.44
    POSITIVE LOGITS
    DockStyle
    0.45
     уви
    0.42
     পথ
    0.41
     кеңсесинде
    0.40
     owning
    0.40
     INDIA
    0.40
    ntity
    0.40
     γν
    0.39
    ra
    0.39
    ==="
    0.39
    Activations Density 0.000%

    No Known Activations