© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132794
    Prev
    Next
    INDEX
    Explanations

    drag and drop within code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }}<
    0.40
    থায়
    0.39
     venous
    0.39
    ទ្ធ
    0.39
     zus
    0.38
    ্যন্তরীণ
    0.38
    utzerklärung
    0.38
     Indies
    0.38
     অত্যা
    0.38
     nitride
    0.38
    POSITIVE LOGITS
    )$.
    0.36
     Ensures
    0.36
     Perfecto
    0.36
     Hampton
    0.36
     ৬০
    0.36
    catch
    0.35
     reverses
    0.35
    一股
    0.35
    
    0.35
     schreibt
    0.34
    Activations Density 0.000%

    No Known Activations