© 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. 60314
    Prev
    Next
    INDEX
    Explanations

    voice comments, hole with, years this

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

    visual programming and algorithms

    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
    鷸
    0.55
    тбол
    0.49
     निमित
    0.47
    둣
    0.45
     үч
    0.44
     maksud
    0.44
    鑄
    0.44
     обучения
    0.44
    筚
    0.44
     săptăm
    0.43
    POSITIVE LOGITS
     and
    0.60
    &
    0.50
     energy
    0.46
    +
    0.46
    and
    0.44
     sogar
    0.44
    et
    0.43
     vascular
    0.43
    UG
    0.43
    ier
    0.42
    Activations Density 0.000%

    No Known Activations