© 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. 57742
    Prev
    Next
    INDEX
    Explanations

    discipline, Holiday, returned

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

    AI generation (video, image, painting)

    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
    以内
    0.47
     variado
    0.46
     Ilmu
    0.45
     Drought
    0.45
     mulig
    0.44
    vió
    0.44
    ũ
    0.44
    قط
    0.43
    tester
    0.43
     Vitória
    0.42
    POSITIVE LOGITS
    rd
    0.51
    ickey
    0.50
     gu
    0.48
    DIRECTION
    0.48
    ec
    0.47
    rw
    0.47
     meanings
    0.47
    ignment
    0.46
     внимание
    0.46
     εκεί
    0.46
    Activations Density 0.000%

    No Known Activations