© 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. 14861
    Prev
    Next
    INDEX
    Explanations

    rate is fixed

    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
     igen
    0.75
     Tucson
    0.75
     zoek
    0.72
     сторона
    0.72
     বাড়ী
    0.72
    رائی
    0.71
     질
    0.71
     οδηγ
    0.70
     넓
    0.68
    ("#
    0.68
    POSITIVE LOGITS
     proclaimed
    0.86
     declared
    0.83
    固定
    0.79
     claramente
    0.78
    declared
    0.76
     ascertained
    0.76
     exposed
    0.75
     quotas
    0.75
     fixed
    0.75
    ructures
    0.74
    Activations Density 0.000%

    No Known Activations