© 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. 10-GEMMASCOPE-RES-131K
    7. 10116
    Prev
    Next
    INDEX
    Explanations

    Delta and its contexts

    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_10/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
    pecabe
    -2.69
    
    -2.56
    榦
    -2.19
     creando
    -2.17
    ドキ
    -2.16
     две
    -2.16
     it
    -2.14
    痾
    -2.14
    UGHTER
    -2.13
    
    -2.13
    POSITIVE LOGITS
    ╿
    2.44
    man
    2.44
    шего
    2.42
    There
    2.38
    ]
    2.34
    One
    2.33
    ;
    2.31
    Most
    2.27
    ꒥
    2.25
    Many
    2.23
    Activations Density 0.008%

    No Known Activations