© 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. 185845
    Prev
    Next
    INDEX
    Explanations

    use around

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

    Ocean Acid

    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
     cookie
    0.53
     #
    0.50
     certify
    0.48
     SSO
    0.46
     anonymously
    0.46
     sulfite
    0.45
     meta
    0.45
     (
    0.45
     cv
    0.44
    то
    0.44
    POSITIVE LOGITS
     damos
    0.52
    ependent
    0.47
    flächen
    0.47
    vär
    0.46
    abetes
    0.46
    nales
    0.46
    ਝ
    0.46
    瓄
    0.46
    ոչ
    0.45
    otional
    0.45
    Activations Density 0.000%

    No Known Activations