© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1010
    Prev
    Next
    INDEX
    Explanations

    kick off, bite force

    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
     Role
    0.67
     suis
    0.66
     nome
    0.65
     દ
    0.65
     హీ
    0.64
     Bulb
    0.63
    嚐
    0.61
     Mens
    0.61
     Σ
    0.61
    ૪
    0.61
    POSITIVE LOGITS
    ings
    2.24
    ability
    2.05
    able
    2.05
    ing
    1.87
    िंग
    1.80
    ables
    1.75
    ers
    1.63
    aways
    1.62
    ingly
    1.59
    nings
    1.55
    Activations Density 0.656%

    No Known Activations