© 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-65K
    7. 4723
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formulas

    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
    frac
    0.93
    Sqrt
    0.90
    ((
    0.84
     ଶ
    0.84
    sqrt
    0.81
     गुणन
    0.81
    arrerol
    0.80
    Ethoxy
    0.80
    FontSize
    0.78
     ८
    0.76
    POSITIVE LOGITS
     specif
    0.65
     metaphor
    0.62
     informants
    0.61
     보안
    0.61
     opinions
    0.59
     offic
    0.58
     humanist
    0.58
     specifically
    0.57
     rant
    0.56
     tenets
    0.55
    Activations Density 0.066%

    No Known Activations