© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 48492
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
     prototypical
    0.48
    ,»
    0.46
    ,’’
    0.46
    ́
    0.45
     isKindOfClass
    0.44
    columnwidth
    0.43
    urètre
    0.42
    endswith
    0.41
    :'],
    0.40
    URLs
    0.40
    POSITIVE LOGITS
     scan
    0.49
    增
    0.45
     .
    0.45
     Scan
    0.44
     scans
    0.44
     scanning
    0.43
     compl
    0.41
     ;
    0.41
    Scan
    0.40
    扫描
    0.39
    Activations Density 0.002%

    No Known Activations