© 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. 14015
    Prev
    Next
    INDEX
    Explanations

    multiples of ten

    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
    ې
    0.77
    ╲
    0.77
    ೕ
    0.76
    <unused11>
    0.74
    漃
    0.74
    <0xA5>
    0.73
    ရား
    0.73
    <strong>
    0.71
    ｼ
    0.71
     $=$
    0.70
    POSITIVE LOGITS
     sixty
    1.58
     fifty
    1.50
     eighty
    1.49
     seventy
    1.44
     thirty
    1.43
     forty
    1.41
    1.40
     ninety
    1.38
     Sixty
    1.35
     साढ़े
    1.32
    Activations Density 0.654%

    No Known Activations