© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 20374
    Prev
    Next
    INDEX
    Explanations

    creative text formats

    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
    広
    1.10
    佺
    1.06
    句话
    1.00
    <unused56>
    0.99
     hecho
    0.99
     menulis
    0.97
    垕
    0.96
     melakukan
    0.95
     функция
    0.95
    }}^{*}\
    0.92
    POSITIVE LOGITS
     uncontroll
    0.83
    from
    0.78
     unanticipated
    0.77
    forth
    0.75
     unforeseen
    0.75
     неожидан
    0.74
    ்ட்
    0.74
     oiled
    0.74
    macht
    0.74
    ters
    0.73
    Activations Density 0.002%

    No Known Activations