© 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. 70266
    Prev
    Next
    INDEX
    Explanations

    non-english text and languages

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

    blocks, image, customer, understand, tags

    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
    OUS
    0.52
    U
    0.52
     leicht
    0.47
     Carrying
    0.47
     CSM
    0.46
     immunoprec
    0.46
     ○
    0.45
     iP
    0.44
    Litt
    0.44
    H
    0.44
    POSITIVE LOGITS
    钴
    0.55
     गोले
    0.54
    进攻
    0.50
    縄
    0.48
    行业的
    0.48
    蜥
    0.48
    美国的
    0.47
     могут
    0.46
    椰
    0.46
    ྥ
    0.46
    Activations Density 0.000%

    No Known Activations