© 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. 75082
    Prev
    Next
    INDEX
    Explanations

    spa, with, March

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

    explaining something to a planet

    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
    րա
    0.49
    vā
    0.47
     पिन
    0.47
    ത്തിനെ
    0.47
    unga
    0.46
    onDidChange
    0.45
    后来
    0.44
    ὼ
    0.44
    re
    0.44
    ар
    0.43
    POSITIVE LOGITS
     M
    0.53
     math
    0.50
     romance
    0.50
     as
    0.48
     already
    0.48
     profes
    0.47
     quote
    0.46
     N
    0.46
     rained
    0.46
     k
    0.46
    Activations Density 0.000%

    No Known Activations