© 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. 164036
    Prev
    Next
    INDEX
    Explanations

    where are

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

    finding, tracking, targeting, decrypting

    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
    الصفحه
    0.48
     اندرو
    0.47
    larım
    0.45
    Radial
    0.45
    learned
    0.44
    悲
    0.44
     اولین
    0.44
    Erik
    0.43
    Katherine
    0.43
    癀
    0.43
    POSITIVE LOGITS
     lends
    0.49
     Gives
    0.49
     televisie
    0.48
     
    0.47
    𒁺
    0.47
     OT
    0.47
     regering
    0.46
     receptors
    0.46
    ző
    0.46
     Sharks
    0.46
    Activations Density 0.000%

    No Known Activations