© 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. 180580
    Prev
    Next
    INDEX
    Explanations

    early nineties or anchor poems

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

    with ingredients and discussions

    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
    ืช
    0.52
     Ủy
    0.49
    чку
    0.48
    хими
    0.47
     Tribunal
    0.46
    カフェ
    0.46
     ट्रॉप
    0.46
    ⟋
    0.44
    ánea
    0.42
     Ethanol
    0.42
    POSITIVE LOGITS
    ص
    0.46
     penso
    0.46
     be
    0.43
     situate
    0.42
     beschrieben
    0.42
     semplic
    0.41
    学历
    0.41
     capazes
    0.41
    QUE
    0.41
    wie
    0.41
    Activations Density 0.000%

    No Known Activations