© 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. 31145
    Prev
    Next
    INDEX
    Explanations

    leather items and their uses

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

    leather things

    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
    EEG
    0.49
     gême
    0.48
    铯
    0.48
     océ
    0.47
     oceanic
    0.47
     simpt
    0.47
    🥦
    0.47
     littoral
    0.47
     océano
    0.46
    पीजी
    0.46
    POSITIVE LOGITS
     leather
    1.52
     Leather
    1.48
    Leather
    1.40
    leather
    1.36
    皮革
    1.32
     レザー
    1.05
    レザー
    1.04
     革
    1.02
    革
    1.02
     кожа
    1.01
    Activations Density 0.087%

    No Known Activations