© 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. 101405
    Prev
    Next
    INDEX
    Explanations

    customers with

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

    demonstrate or imply

    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
    ধার
    0.43
    ষ্ণ
    0.42
    ۰
    0.42
     tecnici
    0.41
     παν
    0.41
    ٠
    0.41
     män
    0.41
    НЫ
    0.40
     tł
    0.40
    ۸
    0.40
    POSITIVE LOGITS
    oed
    0.53
    ']},
    0.46
    ors
    0.44
     Micha
    0.44
    oer
    0.44
    iciones
    0.42
    ovic
    0.42
    ↵↵
    0.42
     Wikispecies
    0.41
    devDependencies
    0.41
    Activations Density 0.000%

    No Known Activations