© 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. 160435
    Prev
    Next
    INDEX
    Explanations

    members walked, options make, work can, needs enormous

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

    different then or here

    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
    </h3>
    0.52
    </strong>
    0.52
    rsquo
    0.48
    read
    0.48
    car
    0.48
     kinder
    0.48
    9
    0.47
     bir
    0.47
     primary
    0.46
    гии
    0.46
    POSITIVE LOGITS
    AsyncKeyState
    0.52
    átiles
    0.50
    akings
    0.48
    MSFont
    0.47
     場所
    0.46
    ներ
    0.46
     diffeomorphism
    0.46
     जड़ों
    0.45
    เศษ
    0.45
    𒌋
    0.45
    Activations Density 0.000%

    No Known Activations