© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6756
    Prev
    Next
    INDEX
    Explanations

    body parts, subjects, and specific terms

    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
     anything
    0.98
     and
    0.94
    ...
    0.92
     ஆகியோர்
    0.89
    --
    0.88
    —
    0.87
    ——
    0.81
     overall
    0.80
     आणि
    0.80
     various
    0.79
    POSITIVE LOGITS
     odnosno
    0.90
    ডি
    0.89
     Selasa
    0.81
     bhikkhave
    0.81
     mesela
    0.81
     }}$,
    0.81
     например
    0.81
     仕事
    0.80
     stung
    0.78
     Kamane
    0.78
    Activations Density 0.396%

    No Known Activations