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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44807
    Prev
    Next
    INDEX
    Explanations

    code snippets and chemical names

    np_acts-logits-general · gemini-2.5-flash-lite

    JavaScript and programming method calls and functions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    .
    -2.81
    та
    -2.80
    ी
    -2.53
    }
    -2.48
    ⸫
    -2.41
    ی
    -2.36
    い
    -2.33
    
    -2.33
    ات
    -2.31
    
    -2.31
    POSITIVE LOGITS
    </strong>
    2.92
    '
    2.42
     is
    2.19
    ться
    2.19
    سبة
    2.16
     мы
    2.06
    </h4>
    2.05
    '];?>
    2.03
    ']?>
    2.02
    }.
    1.96
    Activations Density 0.000%

    No Known Activations