© 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. 126650
    Prev
    Next
    INDEX
    Explanations

    BlackBerry OS, Energy Star compliant

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

    block validation

    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
     Jaaye
    0.53
    iyati
    0.52
     Betty
    0.51
     lão
    0.49
     ಹೊರ
    0.47
     nghĩa
    0.47
     갔
    0.46
     개의
    0.46
     peasantry
    0.46
    ränkt
    0.46
    POSITIVE LOGITS
    ↵↵
    0.44
    าด
    0.43
    eria
    0.42
    िने
    0.42
    са
    0.42
    生命
    0.42
    代替
    0.42
    տ
    0.42
    どう
    0.41
    泳
    0.41
    Activations Density 0.001%

    No Known Activations