© 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. 7411
    Prev
    Next
    INDEX
    Explanations

    hereditary, herding, herpes, herrentag

    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
    ური
    0.84
    ᆨ
    0.84
    underline
    0.83
     boulder
    0.82
    คาร
    0.80
    П
    0.80
     surrogate
    0.78
     priming
    0.76
     lunar
    0.75
    е
    0.75
    POSITIVE LOGITS
     chồng
    1.20
    inafter
    1.16
    ramient
    1.15
    ndon
    1.14
    etically
    1.11
    ული
    1.08
     şeyi
    1.08
    cules
    1.07
    şey
    1.06
    itag
    1.05
    Activations Density 0.059%

    No Known Activations