© 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. 249321
    Prev
    Next
    INDEX
    Explanations

    provide accurate, current, complete information

    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
    শোধ
    0.55
     Alhaji
    0.50
    σης
    0.49
    کروچ
    0.49
    胯
    0.48
    াজি
    0.47
     प्रकृति
    0.47
     rehabilitación
    0.47
    isTouching
    0.47
    LookAndFeelInfo
    0.47
    POSITIVE LOGITS
    "%>
    0.52
    ЕТ
    0.50
    nt
    0.49
    ET
    0.48
    cs
    0.48
     participates
    0.46
    cd
    0.44
    ind
    0.44
    번
    0.44
    ner
    0.44
    Activations Density 0.001%

    No Known Activations