© 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. 28552
    Prev
    Next
    INDEX
    Explanations

    sticky substance

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

    composition and structure

    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
     stomachs
    0.42
     certificado
    0.40
     seas
    0.40
     imposs
    0.40
     biopsies
    0.38
     cé
    0.38
     certificate
    0.37
     紙
    0.37
     সার্টিফিকেট
    0.36
    четов
    0.36
    POSITIVE LOGITS
     anionic
    0.44
    UserId
    0.43
    ionic
    0.43
     الحض
    0.42
     tenta
    0.41
    aly
    0.40
     проблема
    0.38
     kula
    0.38
    𝒍
    0.38
    Method
    0.38
    Activations Density 0.007%

    No Known Activations