© 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. 121829
    Prev
    Next
    INDEX
    Explanations

    additional information or continuation

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

    SQL JOIN and data models

    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
    сня
    0.46
     î
    0.45
     veterinarians
    0.42
     Ginger
    0.41
     Laut
    0.41
    Veter
    0.41
     Gasp
    0.41
    VEMENT
    0.41
     Recognizing
    0.41
     GmbH
    0.40
    POSITIVE LOGITS
    ዢ
    0.52
    <0x93>
    0.46
     escánd
    0.45
    ين
    0.45
     ocasião
    0.44
    бок
    0.44
    ⟥
    0.44
    buje
    0.44
     diligent
    0.44
     Насе
    0.44
    Activations Density 0.000%

    No Known Activations