© 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. 189352
    Prev
    Next
    INDEX
    Explanations

    miniature bargains, becoming monarch

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

    Project presentation

    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
    黐
    0.41
    NERVE
    0.41
    ㇁
    0.41
    ંત્રણ
    0.41
     ಕರೆ
    0.40
    ிஸ்த
    0.40
    ಮೊ
    0.40
    䂘
    0.40
     žmog
    0.39
    <0xE9>
    0.39
    POSITIVE LOGITS
    ЛЕ
    0.45
     restar
    0.43
    হেল
    0.42
     নিম্নলিখিত
    0.41
     themselves
    0.41
     fantastical
    0.41
    нима
    0.40
     их
    0.40
    nehmer
    0.40
     quienes
    0.39
    Activations Density 0.001%

    No Known Activations