© 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. 61987
    Prev
    Next
    INDEX
    Explanations

    common words followed by specific terms

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

    definitions and descriptions following labels

    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
    ')):
    0.52
    گاہ
    0.49
    eluk
    0.49
    edTest
    0.49
    ')){
    0.49
     Consulting
    0.48
    Semif
    0.48
    ']);
    0.47
    BSData
    0.47
    Exercises
    0.46
    POSITIVE LOGITS
     circulate
    0.47
    ร
    0.46
     mince
    0.43
     spinster
    0.43
     lonely
    0.42
    在他的
    0.42
     barracks
    0.41
     engravings
    0.41
     scanty
    0.41
     місце
    0.41
    Activations Density 0.000%

    No Known Activations