© 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. 229115
    Prev
    Next
    INDEX
    Explanations

    fourth quarter

    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
     लैंग्वे
    0.49
     ประเทศ
    0.48
     เตรียม
    0.47
    ському
    0.47
     рестора
    0.47
     あ
    0.46
     条
    0.46
     受け
    0.45
    ৫৪
    0.44
     לע
    0.44
    POSITIVE LOGITS
    only
    0.45
    out
    0.42
     nought
    0.42
    end
    0.41
    divers
    0.41
     gens
    0.39
    bts
    0.39
     glee
    0.38
    transactions
    0.38
    ells
    0.38
    Activations Density 0.001%

    No Known Activations