© 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. 220678
    Prev
    Next
    INDEX
    Explanations

    on average

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

    chicken thighs

    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
    well
    0.50
    gut
    0.48
    arte
    0.47
    artan
    0.47
    arts
    0.47
    :
    0.45
    avelin
    0.44
    :#
    0.44
    <
    0.44
    langle
    0.43
    POSITIVE LOGITS
     Setiap
    0.51
     każde
    0.49
     Every
    0.48
     Règ
    0.48
     setiap
    0.47
     geralmente
    0.47
     reparto
    0.47
    ꒪
    0.47
     Desenvolvimento
    0.46
    마다
    0.46
    Activations Density 0.001%

    No Known Activations