© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94561
    Prev
    Next
    INDEX
    Explanations

    demonstrated his skills

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

    self-acceptance and true grace

    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
    ;">
    0.47
     delinqu
    0.46
     sprouted
    0.45
    /**
    0.44
     deplorable
    0.44
    ↵
    0.41
     blazing
    0.41
    ב
    0.40
     spotting
    0.40
     predatory
    0.39
    POSITIVE LOGITS
     ఉన్నాయి
    0.58
    are
    0.55
     presse
    0.52
     आहेत
    0.52
     Directly
    0.51
     grö
    0.50
    lovakia
    0.48
     吴
    0.48
     सचिवालय
    0.47
     Commonly
    0.47
    Activations Density 0.000%

    No Known Activations