© 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. 89598
    Prev
    Next
    INDEX
    Explanations

    purpose PI

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

    information, inclusion, interests

    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
    ádiz
    0.47
     estancia
    0.43
     Croce
    0.41
     सामान
    0.41
    ,<
    0.40
    প্রাচ
    0.40
    写真を
    0.40
    現代
    0.39
    대를
    0.39
    児
    0.39
    POSITIVE LOGITS
     scaffolds
    0.41
     participa
    0.40
    ীব্র
    0.39
    ৃতা
    0.39
     vote
    0.39
    াকাল
    0.38
     Wrapper
    0.38
     wrapper
    0.38
     zespół
    0.37
     PLoS
    0.37
    Activations Density 0.001%

    No Known Activations