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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2263
    Prev
    Next
    INDEX
    Explanations

    principal amount

    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_262k_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
     financial
    0.66
     long
    0.63
     tent
    0.59
     only
    0.57
     compute
    0.57
     e
    0.56
     "}
    0.56
     &
    0.56
    &
    0.55
     destructive
    0.54
    POSITIVE LOGITS
    miktar
    0.73
    ïde
    0.72
    âte
    0.69
    ifiées
    0.69
    wikkel
    0.68
    cach
    0.68
    äänt
    0.67
     Wight
    0.67
    jsce
    0.66
     rallied
    0.66
    Activations Density 0.000%

    No Known Activations