© 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. 210692
    Prev
    Next
    INDEX
    Explanations

    Berlin Cathedral

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

    replicating ChatGPT

    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
    ו
    0.60
    (
    0.55
    ן
    0.50
    ก
    0.49
    ที
    0.48
    วิ
    0.45
    ם
    0.45
    ละ
    0.44
    ရာ
    0.44
    ною
    0.43
    POSITIVE LOGITS
    চয়
    0.52
     Pots
    0.48
    ग्राउंड
    0.46
     polys
    0.45
     terrible
    0.44
    క్షన్
    0.44
     hello
    0.43
     Bhub
    0.43
    ्यादा
    0.42
     Bedingungen
    0.42
    Activations Density 0.001%

    No Known Activations