© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 80362
    Prev
    Next
    INDEX
    Explanations

    numbers followed by year indicators

    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
     LongNumber
    0.43
     vrem
    0.42
     Bulan
    0.42
     Monthly
    0.42
    лим
    0.42
    膵
    0.41
     jaren
    0.41
    薜
    0.40
    唵
    0.40
     ජී
    0.40
    POSITIVE LOGITS
    god
    0.82
     god
    0.80
    g
    0.74
     g
    0.71
     г
    0.70
     году
    0.65
    г
    0.63
     gods
    0.61
     році
    0.59
    God
    0.57
    Activations Density 0.002%

    No Known Activations