© 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. 157917
    Prev
    Next
    INDEX
    Explanations

    KILL PROCESS

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

    names and foreign words

    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
     transcoding
    0.46
    प्
    0.43
    piry
    0.42
    GRU
    0.42
    ikiem
    0.41
     exporting
    0.40
    ;;)
    0.40
     resultContent
    0.40
     Loire
    0.39
     baron
    0.39
    POSITIVE LOGITS
    um
    0.50
    elis
    0.48
    umlu
    0.47
     מש
    0.44
    wem
    0.42
     ناح
    0.42
    lementine
    0.42
    嗄
    0.41
     على
    0.41
     внутріш
    0.41
    Activations Density 0.000%

    No Known Activations