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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67580
    Prev
    Next
    INDEX
    Explanations

    dangerous range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ὕ
    -1.97
     السياس
    -1.70
    nachweise
    -1.69
    ἵ
    -1.68
    Vastaa
    -1.66
    ἴ
    -1.66
    ί
    -1.55
    ਖ਼
    -1.53
    دکتر
    -1.49
    ὔ
    -1.49
    POSITIVE LOGITS
     your
    2.02
     like
    1.73
     with
    1.54
     get
    1.51
     out
    1.51
     at
    1.49
     situation
    1.45
     before
    1.43
     from
    1.40
     situations
    1.38
    Activations Density 0.018%

    No Known Activations