© 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. 224001
    Prev
    Next
    INDEX
    Explanations

    composer, proper names, or functional words

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

    finding connections or relationships

    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
     :).
    0.55
     поради
    0.51
    A
    0.51
    Bue
    0.50
    Y
    0.49
     Recognizing
    0.49
     in
    0.49
    O
    0.49
     그런
    0.48
    Bare
    0.48
    POSITIVE LOGITS
     কেউই
    0.53
    শিব
    0.47
    ربع
    0.45
     mesin
    0.45
    法則
    0.45
    š
    0.45
    㭋
    0.44
     composés
    0.44
    分數
    0.44
    ها
    0.43
    Activations Density 0.000%

    No Known Activations