© 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. 172497
    Prev
    Next
    INDEX
    Explanations

    work in progress

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

    scene text, documents, code, sexual, recipes

    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
    ’
    0.48
     Templates
    0.47
     Plates
    0.47
     effective
    0.45
     with
    0.45
    y
    0.45
     Lecture
    0.44
     Preservation
    0.43
     effectual
    0.43
    with
    0.43
    POSITIVE LOGITS
     পরও
    0.54
     រ
    0.46
    कील
    0.44
     আরো
    0.44
     Unido
    0.44
    正在
    0.43
    ಿನಿ
    0.43
    libat
    0.43
     इंस्ट
    0.43
     ጋ
    0.43
    Activations Density 0.000%

    No Known Activations