© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54406
    Prev
    Next
    INDEX
    Explanations

    multilingualism and distribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    polarized
    0.42
    opting
    0.42
     combine
    0.41
    log
    0.41
     новой
    0.40
    leve
    0.40
    lang
    0.39
     食
    0.39
    tournament
    0.39
    fonction
    0.38
    POSITIVE LOGITS
     dast
    0.45
     sweetest
    0.45
    𐱅
    0.44
    წ
    0.42
     wort
    0.42
    𝑻
    0.41
    وئ
    0.41
     ternyata
    0.41
     Badan
    0.40
    нная
    0.40
    Activations Density 0.004%

    No Known Activations