© 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. 37016
    Prev
    Next
    INDEX
    Explanations

    common prepositions and determiners

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

    medication or symptoms

    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
     Wicklow
    0.55
     (
    0.48
     Comparable
    0.43
     gx
    0.42
    ഏ
    0.42
    퇴
    0.42
     Акы
    0.42
    _|
    0.41
     Crowd
    0.40
     getHeight
    0.40
    POSITIVE LOGITS
    浻
    0.48
    ignores
    0.47
    𝗷
    0.46
     सर
    0.43
    石
    0.43
    𝗱
    0.42
     ਸੁ
    0.42
     Sari
    0.41
     beğen
    0.41
    瀧
    0.41
    Activations Density 0.000%

    No Known Activations