© 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. 37537
    Prev
    Next
    INDEX
    Explanations

    to let us know

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

    login to or access

    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
     rápidos
    0.44
    پ
    0.43
    utenants
    0.43
     simplistic
    0.43
    STICK
    0.42
     einigen
    0.41
     Inputs
    0.41
    ሎች
    0.41
     고
    0.40
    いくつかの
    0.39
    POSITIVE LOGITS
     yoki
    0.53
     чтобы
    0.50
    ᑉ
    0.49
     ताकि
    0.44
     ដើម្បី
    0.42
     अथवा
    0.42
     inorder
    0.42
     किंवा
    0.42
    facebook
    0.41
    vote
    0.40
    Activations Density 0.003%

    No Known Activations