© 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. 38618
    Prev
    Next
    INDEX
    Explanations

    works

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

    planning stages and outcomes

    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
     hoteles
    0.48
     convertible
    0.48
     Argentina
    0.47
     assorted
    0.45
     revenues
    0.44
     payouts
    0.44
     Expedia
    0.44
    :
    0.44
     Deccan
    0.44
     Argentine
    0.43
    POSITIVE LOGITS
    ContentAlignment
    0.57
    进而
    0.52
    此同时
    0.51
    不断的
    0.50
    的过程
    0.48
     магистра
    0.47
    ﹙
    0.46
     processos
    0.46
     этап
    0.46
    坵
    0.45
    Activations Density 0.000%

    No Known Activations