© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 248561
    Prev
    Next
    INDEX
    Explanations

    Respondent followed by legal terminology

    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
    är
    0.48
    ეგ
    0.46
    номет
    0.46
    Cryptography
    0.45
    ан
    0.45
    osomal
    0.45
    𝘰
    0.45
    福祉
    0.44
    סי
    0.44
    мал
    0.44
    POSITIVE LOGITS
     Alors
    0.50
     Kyle
    0.48
     Alh
    0.46
     Proud
    0.45
    ᄃ
    0.45
     Planet
    0.45
     SMEs
    0.45
     Ard
    0.45
     للن
    0.44
     مذا
    0.44
    Activations Density 0.001%

    No Known Activations