© 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. 216591
    Prev
    Next
    INDEX
    Explanations

    disposal regarding, not condemn, checkbox state

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

    immediately; wage changes

    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
    cion
    0.49
    ྫ
    0.47
    zón
    0.46
    िकी
    0.46
    铎
    0.46
     manager
    0.46
    镛
    0.45
     मान
    0.45
    fini
    0.44
    厂
    0.44
    POSITIVE LOGITS
     ambito
    0.57
    -',
    0.51
    *",
    0.48
    shim
    0.47
    Ow
    0.46
     unbek
    0.45
    *',
    0.44
    scope
    0.44
     '',
    0.44
    work
    0.44
    Activations Density 0.000%

    No Known Activations