© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29469
    Prev
    Next
    INDEX
    Explanations

    potentially, hiking, river, grass, servers

    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
     형태
    0.48
     बैचलर्स
    0.46
     janu
    0.46
     کی۔
    0.45
    立
    0.43
     personalisation
    0.42
     копия
    0.42
     Фурга
    0.42
    Transcription
    0.42
    ♰
    0.42
    POSITIVE LOGITS
    aw
    0.54
    一
    0.48
    awan
    0.47
     gutter
    0.47
    the
    0.46
    ui
    0.45
    ai
    0.42
    sn
    0.42
    看着
    0.41
     magari
    0.41
    Activations Density 0.003%

    No Known Activations