© 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. 247572
    Prev
    Next
    INDEX
    Explanations

    mere fact or meeting

    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
     oreilles
    0.49
     efficaces
    0.45
     اسرائیل
    0.44
     அதிகம்
    0.44
     ચા
    0.43
    Underwater
    0.43
     frowned
    0.42
    忶
    0.42
     stessi
    0.42
     Islands
    0.42
    POSITIVE LOGITS
     geh
    0.47
     contentService
    0.45
     וכ
    0.42
    spring
    0.42
     hoi
    0.42
     h
    0.41
     winter
    0.40
    ৈ
    0.40
     давно
    0.40
    ptica
    0.39
    Activations Density 0.001%

    No Known Activations