© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4284
    Prev
    Next
    INDEX
    Explanations

    spine, binding, leather, lettering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividad
    0.46
     ऑफलाइन
    0.46
     жүктөп
    0.45
    CHEC
    0.44
    oplayer
    0.42
    ɽ
    0.42
    baix
    0.42
     remixes
    0.42
    トゥーン
    0.42
     phas
    0.41
    POSITIVE LOGITS
     spine
    1.16
     Spine
    0.95
    spine
    0.94
     spines
    0.93
     hardcover
    0.79
     SPINE
    0.76
     Publishers
    0.72
    脊
    0.71
     binding
    0.71
     gilt
    0.66
    Activations Density 0.003%

    No Known Activations