© 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. 5399
    Prev
    Next
    INDEX
    Explanations

    numbers

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

    numbers in lists

    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
     વસ્તુ
    0.44
     insanın
    0.41
     ముఖ్య
    0.41
     erforderlich
    0.41
     photosynthesis
    0.40
    ⌝
    0.40
    کومت
    0.40
    letscher
    0.39
     począ
    0.38
    бычно
    0.38
    POSITIVE LOGITS
     five
    1.06
     eight
    1.06
     six
    1.03
     seven
    1.01
    6
    0.99
     three
    0.96
    4
    0.96
     four
    0.94
     nine
    0.94
    7
    0.94
    Activations Density 0.127%

    No Known Activations