© 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. 135722
    Prev
    Next
    INDEX
    Explanations

    Torres Strait Islander

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

    short description of 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
     PROBLE
    0.49
     coche
    0.48
    ிருக்கு
    0.45
     SOCI
    0.43
     PAST
    0.43
     CHILD
    0.42
    P
    0.42
    🚗
    0.41
    T
    0.41
    L
    0.41
    POSITIVE LOGITS
     tensors
    0.45
     postings
    0.44
    CLC
    0.43
     খানের
    0.43
    UTONIUM
    0.42
     کی۔
    0.41
    ency
    0.39
     fellows
    0.39
    errick
    0.38
    CCCN
    0.38
    Activations Density 0.001%

    No Known Activations