© 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-262K
    7. 12000
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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_262k_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
     друга
    0.44
    шее
    0.38
     tantôt
    0.38
     neka
    0.37
    阌
    0.37
     নামক
    0.37
    打了
    0.37
    抹
    0.36
     nuevas
    0.36
    들의
    0.36
    POSITIVE LOGITS
     आपसे
    0.43
    Air
    0.39
    Univ
    0.38
     dimiliki
    0.36
     Lin
    0.36
     Hop
    0.36
    Jay
    0.35
    atzen
    0.35
    Once
    0.35
    all
    0.35
    Activations Density 0.067%

    No Known Activations