© 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. 208512
    Prev
    Next
    INDEX
    Explanations

    denotes, podcast, collecting, visited

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

    is true

    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
     Charley
    0.49
     Shades
    0.46
     Hayes
    0.45
     Barlow
    0.44
     Schlaf
    0.42
     Casper
    0.42
    耑
    0.42
    การ
    0.42
    }^{*}$.
    0.42
     Fanny
    0.40
    POSITIVE LOGITS
     ބ
    0.52
     Новости
    0.48
     Нов
    0.47
     ಸೇ
    0.47
     commissioned
    0.46
     indist
    0.46
    গন্ধ
    0.46
     quieran
    0.46
     incluso
    0.45
     うち
    0.45
    Activations Density 0.000%

    No Known Activations