© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 712
    Prev
    Next
    INDEX
    Explanations

    love this

    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
    哢
    -1.86
    рення
    -1.77
     juſ
    -1.62
     排骨
    -1.62
     bermanfaat
    -1.55
     ſch
    -1.52
     specialize
    -1.52
    ﮦ
    -1.52
    ੴ
    -1.52
    ейчас
    -1.48
    POSITIVE LOGITS
    )
    1.86
     charismatic
    1.85
    ("
    1.73
    }$
    1.62
    );
    
    1.59
     are
    1.49
     как
    1.49
     ويت
    1.48
     love
    1.48
    。"
    1.48
    Activations Density 0.028%

    No Known Activations