© 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. 22-GEMMASCOPE-2-RES-65K
    7. 7129
    Prev
    Next
    INDEX
    Explanations

    Syd Mead, Lidocaine, clonidine

    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_22_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
    ยัง
    1.39
     quizz
    1.22
    けど
    1.20
     withstood
    1.18
     revenus
    1.17
    о
    1.17
    ‌تر
    1.16
     headroom
    1.15
     rendez
    1.15
     residuos
    1.13
    POSITIVE LOGITS
    ゥ
    2.19
    ependent
    2.06
    olph
    2.06
    nesday
    1.98
    ଼
    1.98
    imension
    1.95
    ifferent
    1.93
    ynamics
    1.92
    irect
    1.91
    ding
    1.90
    Activations Density 0.650%

    No Known Activations