© 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-65K
    7. 749
    Prev
    Next
    INDEX
    Explanations

    code block endings and explanations

    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
    (
    0.89
    es
    0.73
    is
    0.69
    en
    0.66
    Sa
    0.65
    tr
    0.65
    se
    0.63
    sa
    0.63
    an
    0.63
    Buck
    0.62
    POSITIVE LOGITS
    ServiceGroupID
    0.82
    <unused756>
    0.81
     fichier
    0.80
    ódulo
    0.79
     proporciona
    0.78
    <unused394>
    0.77
     texId
    0.77
     proporcionan
    0.77
     comentado
    0.77
     karşılaş
    0.75
    Activations Density 0.195%

    No Known Activations