© 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. 49602
    Prev
    Next
    INDEX
    Explanations

    foreign language descriptions

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

    metabolism, Renewable, USA, Load, AS

    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
     parameters
    0.48
    ͗
    0.48
     uit
    0.46
     nang
    0.45
    parameters
    0.44
     hou
    0.44
     storing
    0.43
    ''''
    0.43
     industriale
    0.43
     parámetros
    0.42
    POSITIVE LOGITS
    اللہ
    0.45
    কর্ম
    0.43
    標
    0.43
    紮
    0.41
     Journalism
    0.41
    幼稚
    0.40
    倖
    0.39
    ధిక
    0.39
     Journalists
    0.38
    σή
    0.38
    Activations Density 0.000%

    No Known Activations