© 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. 43885
    Prev
    Next
    INDEX
    Explanations

    beyond scope or larger scale

    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
     abruptly
    0.46
    《
    0.43
    freq
    0.40
    A
    0.40
    ahrt
    0.38
     оружия
    0.38
    lamiento
    0.38
    是一位
    0.38
    ख
    0.38
    妊娠
    0.38
    POSITIVE LOGITS
     общий
    0.49
     seront
    0.46
     chaque
    0.46
     serão
    0.46
     będą
    0.46
     tatou
    0.45
     custList
    0.45
     thermost
    0.45
     comma
    0.44
     donut
    0.44
    Activations Density 0.004%

    No Known Activations