© 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. 194316
    Prev
    Next
    INDEX
    Explanations

    very mom

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

    cause unpredictable

    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
     использу
    0.45
    Great
    0.44
     Büyük
    0.43
    '
    0.42
    좀
    0.42
     Volumen
    0.41
     Trilogy
    0.40
     ترجم
    0.39
    â
    0.39
     फ्लैट
    0.39
    POSITIVE LOGITS
     こと
    0.45
     mik
    0.44
    েন্দ্র
    0.44
     দফ
    0.44
     ભે
    0.43
    諧
    0.43
     още
    0.42
    θυ
    0.42
    pentine
    0.42
    囉
    0.42
    Activations Density 0.000%

    No Known Activations