© 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. 102788
    Prev
    Next
    INDEX
    Explanations

    appetite and anorexia

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

    words related to appetite and food consumption.

    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
    ‘
    -2.55
    я
    -2.50
    櫚
    -2.48
    It
    -2.45
    
    -2.41
    鱻
    -2.23
     \_
    -2.20
    N
    -2.20
    \
    -2.16
    POSITIVE LOGITS
    墻
    2.22
    挹
    2.19
    冢
    2.14
    也得
    2.11
     zestawie
    2.06
    <bos>
    2.06
    }
    2.05
    ୩
    2.03
     gloomy
    2.03
    뻑
    2.00
    Activations Density 0.004%

    No Known Activations