© 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. 15282
    Prev
    Next
    INDEX
    Explanations

    detector, parentheses, share

    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
     cnv
    0.89
     отличается
    0.87
    ),”
    0.87
     mammalian
    0.86
     மேற்பட்ட
    0.85
    ुणा
    0.82
     overloaded
    0.82
    넌
    0.81
     sowas
    0.80
    ሰ
    0.80
    POSITIVE LOGITS
     photos
    0.78
    ප්
    0.77
     typo
    0.77
    pril
    0.76
     Excise
    0.72
     outcomes
    0.72
    /(
    0.72
    OID
    0.70
     ular
    0.70
    images
    0.70
    Activations Density 0.000%

    No Known Activations