© 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. 241909
    Prev
    Next
    INDEX
    Explanations

    continue reading

    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
     LORD
    0.47
    Conv
    0.46
     DRAM
    0.45
     Chỉ
    0.45
     Budget
    0.44
     Conv
    0.44
    膠
    0.44
     Offering
    0.44
    紗
    0.43
    ല്‍
    0.42
    POSITIVE LOGITS
     enkele
    0.55
    andal
    0.52
    ü
    0.52
     다양
    0.49
     independência
    0.48
     einige
    0.45
    ähn
    0.45
     contento
    0.45
     মুক্তিযোদ্ধা
    0.44
     خوب
    0.44
    Activations Density 0.001%

    No Known Activations