© 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. 14292
    Prev
    Next
    INDEX
    Explanations

    emojis and foreign scripts

    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
     nurture
    0.82
    ativeness
    0.81
    ^{*}}{\
    0.79
    €™
    0.78
    이트
    0.78
    ंत
    0.78
    oo
    0.77
    ^{
    0.77
     selectInput
    0.76
    astype
    0.76
    POSITIVE LOGITS
    ricult
    1.10
    𝗶
    1.07
    Ｍ
    1.02
     Inoltre
    1.01
     Bisby
    1.00
    Alternatively
    1.00
    및
    1.00
    ਰ
    0.99
    ности
    0.97
    그러나
    0.96
    Activations Density 0.001%

    No Known Activations