© 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. 174620
    Prev
    Next
    INDEX
    Explanations

    negotiate or get

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

    boundaries, frameworks, finds, key, knuckles

    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
     gross
    0.53
     condiments
    0.51
     d
    0.50
     absolutely
    0.50
     e
    0.49
    ,
    0.49
     Caps
    0.48
     conformation
    0.47
     commodities
    0.46
     excerpts
    0.46
    POSITIVE LOGITS
     न्याय
    0.51
    hiddenMap
    0.51
     наличии
    0.50
    䄪
    0.50
    spiderX
    0.50
     нацыяна
    0.49
    俦
    0.48
     нашли
    0.48
    ഽ
    0.48
     Königreich
    0.47
    Activations Density 0.000%

    No Known Activations