© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 20133
    Prev
    Next
    INDEX
    Explanations

    skin feeling or messes with

    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
    ​
    0.43
    "`
    0.43
    ocat
    0.42
    otos
    0.40
    ynch
    0.40
     Lant
    0.40
    </td>
    0.39
     Inbox
    0.39
    optic
    0.39
    opt
    0.38
    POSITIVE LOGITS
     seulement
    0.44
     suficientemente
    0.44
     лише
    0.43
    byshev
    0.43
     толькі
    0.43
     keresztül
    0.43
    केवल
    0.43
    Ꮈ
    0.43
     त्वचा
    0.42
    verläss
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.