© 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. 47397
    Prev
    Next
    INDEX
    Explanations

    fabric type names

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

    clothing 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
    r
    0.48
    t
    0.47
     Osmanlı
    0.45
     Investment
    0.44
     NYC
    0.44
    ruth
    0.43
    i
    0.43
     ختم
    0.43
     Multi
    0.42
     Burma
    0.41
    POSITIVE LOGITS
     mistrust
    0.63
     distrust
    0.52
    寂
    0.52
     tissue
    0.50
     vacío
    0.50
     parenchyma
    0.50
    蟎
    0.50
     energía
    0.50
     estrés
    0.49
    恐怖
    0.49
    Activations Density 0.001%

    No Known Activations