© 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. 245647
    Prev
    Next
    INDEX
    Explanations

    trusted software or other specific terms

    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
    K
    0.47
     beloved
    0.46
    M
    0.46
    腊
    0.45
     lavish
    0.44
    М
    0.43
     فن
    0.43
    spac
    0.43
     extravag
    0.43
    R
    0.42
    POSITIVE LOGITS
    囩
    0.54
    слі
    0.46
    :'',
    0.46
    䢀
    0.44
    Supplier
    0.44
     comenzamos
    0.43
     እነዚህ
    0.43
     maximale
    0.43
    راتكم
    0.43
    getBlock
    0.42
    Activations Density 0.001%

    No Known Activations