© 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. 42058
    Prev
    Next
    INDEX
    Explanations

    many years

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

    Sun and Moon

    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
    ছাই
    0.49
    ிழ
    0.49
    䤃
    0.49
    новить
    0.48
     grossesse
    0.47
    ліся
    0.47
    𝘷
    0.46
    䡈
    0.46
    स्वी
    0.45
    ně
    0.45
    POSITIVE LOGITS
     uses
    0.47
     .
    0.45
     hone
    0.42
     wall
    0.41
     শহরে
    0.41
     joined
    0.40
    くちゃ
    0.40
    ↵
    0.40
     hilly
    0.39
     iterating
    0.39
    Activations Density 0.000%

    No Known Activations