© 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. 38169
    Prev
    Next
    INDEX
    Explanations

    Thoreau's Walden Pond solitude

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

    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-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
     ఖ
    0.44
     ಖ
    0.44
    掟
    0.44
     definición
    0.42
     principalColumn
    0.41
     hepinize
    0.40
     risked
    0.39
    恐
    0.39
    🇭
    0.38
    英國
    0.38
    POSITIVE LOGITS
     Thoreau
    0.93
    Thoreau
    0.83
     Emerson
    0.52
     transcendental
    0.50
     Transcend
    0.49
     Bhag
    0.49
     Adirond
    0.48
    Boston
    0.47
     Alps
    0.47
     afternoons
    0.47
    Activations Density 0.004%

    No Known Activations