© 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. 174572
    Prev
    Next
    INDEX
    Explanations

    truffles, carrots, looked terrible, status light

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

    brand personality, story format, potential design, flooring options

    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
    ÂN
    0.52
    ኃ
    0.50
    ﺎ
    0.50
    зіно
    0.47
    اک
    0.47
    ھوں
    0.45
    ю
    0.44
     :,
    0.44
    ändern
    0.44
     comparison
    0.43
    POSITIVE LOGITS
     swirls
    0.46
     Pillow
    0.44
     crevices
    0.44
     abyss
    0.44
    იმ
    0.43
    opia
    0.43
    eteenth
    0.43
    យើង
    0.42
     తాజాగా
    0.42
     crum
    0.42
    Activations Density 0.000%

    No Known Activations