© 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. 79398
    Prev
    Next
    INDEX
    Explanations

    fact that, permitted on, drying levels, throttle up

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

    concepts and their properties

    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
    <body>
    0.44
    ér
    0.44
    publisher
    0.42
    または
    0.42
     、
    0.41
    oste
    0.41
    거나
    0.40
    醫師
    0.40
    escal
    0.39
     is
    0.39
    POSITIVE LOGITS
     liturg
    0.45
    న్న
    0.45
    Haha
    0.43
    닼
    0.43
    ႃႇ
    0.43
     permis
    0.42
    꿨
    0.42
     இருந்த
    0.41
    ಲ್ಪ
    0.41
     Bereiche
    0.41
    Activations Density 0.001%

    No Known Activations