© 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. 24976
    Prev
    Next
    INDEX
    Explanations

    chemical names with numbers and hyphens

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

    chemical name prefixes and numbers

    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
     सर्कल
    0.49
    碼
    0.44
    πά
    0.44
     সীমান্তের
    0.43
    ασία
    0.42
    କୁ
    0.41
    人們
    0.41
     সীমান্তে
    0.41
    യാണ്
    0.40
    比如
    0.40
    POSITIVE LOGITS
    habilit
    0.50
     storied
    0.45
    -
    0.45
    ż
    0.45
    ‐
    0.44
    ž
    0.44
     freshly
    0.44
    țele
    0.43
    fluor
    0.42
     unfolded
    0.42
    Activations Density 0.008%

    No Known Activations