© 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. 224601
    Prev
    Next
    INDEX
    Explanations

    images and specific terms

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

    traditional change, rely on, messy classroom

    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
    anter
    0.46
    arin
    0.42
    在
    0.41
     repayments
    0.41
    anj
    0.40
     repayment
    0.40
    jen
    0.40
    ynd
    0.40
    etis
    0.40
    ma
    0.39
    POSITIVE LOGITS
     Bridg
    0.60
    画像を
    0.51
     viy
    0.49
     Perfectly
    0.49
    बिर
    0.47
    નું
    0.47
    Brid
    0.46
     {}>,
    0.46
     সংখ্যক
    0.46
     dimensionality
    0.45
    Activations Density 0.001%

    No Known Activations