© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28598
    Prev
    Next
    INDEX
    Explanations

    services and maintenance

    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
     to
    -1.41
     from
    -1.23
     pieces
    -1.17
    させて頂きます
    -1.16
    r
    -1.14
    b
    -1.14
    -
    -1.13
    P
    -1.11
    m
    -1.11
    ta
    -1.11
    POSITIVE LOGITS
    prakti
    1.32
    ığımız
    1.21
    lichten
    1.20
    潆
    1.16
    |}\
    1.16
    AÇÃO
    1.14
    AfterViewInit
    1.13
    }%
    
    1.13
    asyarakat
    1.12
    ofte
    1.11
    Activations Density 0.039%

    No Known Activations