© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14874
    Prev
    Next
    INDEX
    Explanations

    physical features of creatures

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

    body parts and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partenaire
    0.43
     trám
    0.41
     Leitung
    0.41
    缆
    0.41
     পলিপ
    0.40
     sám
    0.40
     سنگ
    0.39
    itäts
    0.39
     листь
    0.39
    Sunflower
    0.39
    POSITIVE LOGITS
     agile
    0.41
    גר
    0.40
     proportionately
    0.40
     somewhat
    0.39
     corred
    0.39
    }},
    0.39
     almost
    0.38
     deprecated
    0.38
    FindingsResponse
    0.38
     proportionally
    0.38
    Activations Density 0.019%

    No Known Activations