© 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. 136229
    Prev
    Next
    INDEX
    Explanations

    local disk drives

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

    cost and consequences

    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
     வரவேற்ப
    0.50
    ಗಾರ
    0.50
     約
    0.48
    bearer
    0.45
     Gefühl
    0.45
     eğ
    0.44
     rappeler
    0.44
     உள்ள
    0.44
    bear
    0.44
     ursprünglich
    0.44
    POSITIVE LOGITS
     palavras
    0.50
    hui
    0.48
    atemala
    0.46
    وان
    0.46
    atique
    0.46
    ت
    0.46
    RIO
    0.45
    ات
    0.45
    تك
    0.45
    IPE
    0.45
    Activations Density 0.000%

    No Known Activations