© 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. 71345
    Prev
    Next
    INDEX
    Explanations

    code and non-english words

    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
     BehaviorSubject
    -1.27
     by
    -1.27
     also
    -1.26
     vulgaires
    -1.15
     for
    -1.15
     to
    -1.15
     malheur
    -1.14
    ;%%
    -1.13
    Elaboración
    -1.13
    
    -1.13
    POSITIVE LOGITS
    <eos>
    1.41
     installiert
    1.25
     and
    1.22
    无疑
    1.15
    ఝ
    1.13
     baskılı
    1.11
    誰か
    1.11
    まさかの
    1.08
    Desired
    1.07
    こいつ
    1.07
    Activations Density 0.007%

    No Known Activations