© 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. 24199
    Prev
    Next
    INDEX
    Explanations

    progress and status updates

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

    degree levels

    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
    {-#
    0.41
    xie
    0.40
    ುದ
    0.40
    ऊं
    0.39
    预
    0.39
    strual
    0.38
     ভরে
    0.38
    Usually
    0.37
    有时候
    0.37
    afat
    0.37
    POSITIVE LOGITS
     consideramos
    0.51
     evolução
    0.50
     huidige
    0.48
     nagyon
    0.47
     progreso
    0.47
     digitalen
    0.47
    ك
    0.47
     porque
    0.46
     جیسا
    0.46
     jossa
    0.46
    Activations Density 0.000%

    No Known Activations