© 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. 48608
    Prev
    Next
    INDEX
    Explanations

    part of a phrase

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

    slightly overwhelming

    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
    c
    0.58
    la
    0.52
    os
    0.52
    d
    0.48
    b
    0.47
    x
    0.47
    reef
    0.46
    wa
    0.46
    ase
    0.44
    waters
    0.44
    POSITIVE LOGITS
    蒿
    0.49
    зге
    0.48
    Expire
    0.48
    вете
    0.47
    Modify
    0.47
    лай
    0.46
    爍
    0.46
     задача
    0.46
     সবগুলো
    0.46
    猾
    0.46
    Activations Density 0.000%

    No Known Activations