© 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. 96543
    Prev
    Next
    INDEX
    Explanations

    fine, failure, offering, pay

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

    "nigiri", "factor", "New York", "bicycle", "Les chats"

    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
     frightened
    0.46
     स्किल
    0.46
    팝
    0.46
     frightening
    0.45
    न्ने
    0.44
     cumin
    0.44
     suma
    0.44
    Complexity
    0.44
    PRICE
    0.44
     tuna
    0.43
    POSITIVE LOGITS
    слав
    0.51
     собою
    0.47
    cutting
    0.47
    <0xCD>
    0.46
    RestController
    0.46
    crast
    0.46
    kend
    0.46
    cut
    0.46
    ское
    0.46
    光的
    0.46
    Activations Density 0.000%

    No Known Activations