© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169021
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and nouns

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

    local transactions

    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
     ઝડ
    0.48
    '_{\
    0.47
    ल्पनिक
    0.46
    黯
    0.46
    рг
    0.45
    觞
    0.45
    Վ
    0.44
    Underwater
    0.43
    ườn
    0.43
    prepare
    0.42
    POSITIVE LOGITS
     holidays
    0.45
    ově
    0.45
    ÍC
    0.44
    azion
    0.43
     feedstock
    0.43
    z
    0.42
     betracht
    0.42
     bleach
    0.42
     kilometres
    0.41
    />}
    0.40
    Activations Density 0.001%

    No Known Activations