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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 145367
    Prev
    Next
    INDEX
    Explanations

    written by, could wish, follow trends

    np_acts-logits-general · gemini-2.5-flash-lite

    list items punctuation or 'or'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ت
    0.52
    物を
    0.46
    モノ
    0.45
     Beaut
    0.44
     کار
    0.43
     jurídico
    0.43
     پا
    0.42
    ナトリウム
    0.42
     démont
    0.41
     میچ
    0.41
    POSITIVE LOGITS
    zilla
    0.46
    zny
    0.43
    zle
    0.42
    yeh
    0.41
    依
    0.41
    Judging
    0.41
    >')
    0.40
    员
    0.40
    শাসন
    0.40
    妹
    0.40
    Activations Density 0.003%

    No Known Activations