© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 4851
    Prev
    Next
    INDEX
    Explanations

    percentages of

    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
    ফে
    0.96
    es
    0.95
     half
    0.93
    وا
    0.92
    ா
    0.90
    Bo
    0.87
    েন
    0.86
     kij
    0.85
    quando
    0.84
    ഷി
    0.84
    POSITIVE LOGITS
    <0xD8>
    1.29
     chance
    1.27
    matplotlib
    1.26
     humidity
    1.15
     affiliation
    1.15
     dotycz
    1.12
    twenty
    1.11
     ABV
    1.10
     участие
    1.09
     ofthe
    1.09
    Activations Density 0.096%

    No Known Activations