© 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. 143999
    Prev
    Next
    INDEX
    Explanations

    series and fish

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

    use code

    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
    ες
    0.51
    ਕੇ
    0.51
    দিগকে
    0.50
    languageTag
    0.50
    essen
    0.50
     ءِ
    0.49
    operateur
    0.48
     lokalen
    0.47
    teman
    0.47
    carbam
    0.47
    POSITIVE LOGITS
     which
    0.53
    раз
    0.53
     body
    0.52
    If
    0.52
    1
    0.51
     öğ
    0.50
     İ
    0.50
    وي
    0.50
     hurry
    0.48
     stabilizes
    0.48
    Activations Density 0.001%

    No Known Activations