© 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. 177799
    Prev
    Next
    INDEX
    Explanations

    predict that / judgment

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

    acts-as-taggable-on, Fear the Walking Dead, Mindful Habits

    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
     ここ
    0.61
    trim
    0.57
    trimmed
    0.57
    configured
    0.54
    たん
    0.51
    변경된
    0.51
     ソ
    0.49
    fer
    0.49
    fl
    0.49
    compress
    0.49
    POSITIVE LOGITS
     predation
    0.47
    பால்
    0.46
     Besoin
    0.44
    OfString
    0.43
    헛
    0.42
     issu
    0.41
    旬
    0.41
     Raum
    0.41
    Understanding
    0.41
     господар
    0.41
    Activations Density 0.000%

    No Known Activations