© 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. 143878
    Prev
    Next
    INDEX
    Explanations

    updates and scheduled events

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

    but, despite qualifications

    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
     પરંતુ
    0.54
    ༧
    0.53
    છ
    0.51
     መሰ
    0.49
     વાંચો
    0.49
    ৱ
    0.48
    퉁
    0.48
    ੈ
    0.48
    濯
    0.48
    ું
    0.48
    POSITIVE LOGITS
     envo
    0.49
    五十
    0.46
     attuale
    0.46
     ACh
    0.46
     credo
    0.45
     envoy
    0.43
     hei
    0.43
     Vinh
    0.43
     fashionable
    0.42
     temer
    0.42
    Activations Density 0.001%

    No Known Activations