© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38169
    Prev
    Next
    INDEX
    Explanations

    Thoreau, Emerson, Walden

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     definición
    0.40
     ಖ
    0.38
    恐
    0.38
    確率
    0.38
     ఖ
    0.37
    atinum
    0.37
    階段
    0.37
    🇭
    0.36
    正式
    0.36
    怒
    0.36
    POSITIVE LOGITS
     Thoreau
    1.00
    Thoreau
    0.84
     Transcend
    0.56
     Emerson
    0.53
     transcendental
    0.53
     Adirond
    0.50
     Walden
    0.50
     Bhag
    0.50
     Tufts
    0.50
     Blueberry
    0.48
    Activations Density 0.004%

    No Known Activations