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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 533
    Prev
    Next
    INDEX
    Explanations

    software templates

    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
     Extensive
    -2.23
     be
    -2.20
     esche
    -2.14
     he
    -2.13
    }
    -2.08
     Helps
    -2.06
    傒
    -2.03
     Important
    -1.96
    要在
    -1.96
     chug
    -1.93
    POSITIVE LOGITS
    ↵
    2.67
    ſſel
    2.20
    templates
    2.13
     хорошем
    2.09
     cheerful
    2.09
     observar
    2.06
    雳
    2.05
    傥
    2.03
     supremely
    2.02
    
    1.98
    Activations Density 0.007%

    No Known Activations