© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2782
    Prev
    Next
    INDEX
    Explanations

    scientific concepts and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Temperatura
    0.81
     fickle
    0.75
    新しい
    0.75
     كيفية
    0.74
     ಶು
    0.74
    <unused2003>
    0.73
    cómo
    0.73
    <unused1159>
    0.73
     controllable
    0.72
     새로운
    0.72
    POSITIVE LOGITS
     moiety
    1.03
     system
    1.00
     regime
    0.99
     signal
    0.97
     signals
    0.94
     region
    0.88
     spectrum
    0.87
     versus
    0.87
     vs
    0.84
     domain
    0.84
    Activations Density 0.173%

    No Known Activations