© 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. 9753
    Prev
    Next
    INDEX
    Explanations

    superheroes

    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
    xi
    -1.52
    _
    -1.34
    方の
    -1.27
    ";
    -1.26
    displaystyle
    -1.23
     $
    -1.20
    方に
    -1.17
    ".
    -1.17
     السياس
    -1.16
    commerce
    -1.15
    POSITIVE LOGITS
     ativar
    1.43
    噐
    1.38
    توضیحات
    1.36
    ёх
    1.30
    というわけで
    1.30
     貓
    1.30
    作り方
    1.30
     Feinde
    1.28
     lutar
    1.27
    栝
    1.27
    Activations Density 0.033%

    No Known Activations