© 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. 32959
    Prev
    Next
    INDEX
    Explanations

    word followed by specific punctuation or type

    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
     ORDERS
    0.53
    ጁ
    0.53
     FITNESS
    0.51
    ጇ
    0.50
     ADMINISTR
    0.50
     READY
    0.49
     человека
    0.48
     যার
    0.48
    謊
    0.47
     INSTR
    0.47
    POSITIVE LOGITS
    t
    0.56
    permit
    0.53
    PA
    0.53
    terminate
    0.53
    n
    0.52
    py
    0.52
    glob
    0.52
    donate
    0.51
    download
    0.51
    tmp
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.