Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 19650
    Prev
    Next
    INDEX
    Explanations

    presence of following words

    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
     statistiques
    0.71
    สมัย
    0.69
    헤
    0.65
    든지
    0.64
     واله
    0.60
    शे
    0.60
    rotnie
    0.60
    논
    0.59
     své
    0.58
    /).
    0.58
    POSITIVE LOGITS
     presence
    2.12
     removal
    1.92
     наличие
    1.90
     présence
    1.82
    presence
    1.82
     adanya
    1.75
     creation
    1.75
     وجود
    1.72
     presenza
    1.66
     inclusion
    1.66
    Activations Density 0.102%

    No Known Activations