© 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. 28509
    Prev
    Next
    INDEX
    Explanations

    material, design, goods, connection

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

    material or materials

    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
    в
    0.80
    OR
    0.74
    arı
    0.70
    ari
    0.69
    श
    0.66
    ਮ
    0.65
    ש
    0.65
    타
    0.65
    ता
    0.64
    ली
    0.64
    POSITIVE LOGITS
     Materialien
    1.34
     Materials
    1.31
     Material
    1.19
     anyag
    1.18
     素材
    1.17
    Materials
    1.15
     materiale
    1.15
     मटेरियल
    1.15
     المواد
    1.14
     materials
    1.12
    Activations Density 0.039%

    No Known Activations