© 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. 54404
    Prev
    Next
    INDEX
    Explanations

    reading society versions

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

    user home configuration files

    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
     ጨ
    0.46
     لوبی
    0.44
    कॉ
    0.44
    ਓ
    0.43
     கிட்டத்தட்ட
    0.42
    ת
    0.42
    }}$$
    0.42
     શું
    0.42
    🍛
    0.42
    மல
    0.42
    POSITIVE LOGITS
     Fairfax
    0.42
    ายน
    0.41
     Pantry
    0.39
     composer
    0.39
     politik
    0.38
     repeatable
    0.38
     finitely
    0.38
     regenerate
    0.37
     villa
    0.37
     savory
    0.37
    Activations Density 0.008%

    No Known Activations