© 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. 106190
    Prev
    Next
    INDEX
    Explanations

    independently established

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

    specific implementation

    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
     Challenges
    0.48
    哣
    0.46
     convexe
    0.44
    තු
    0.44
    Mn
    0.44
    鸡
    0.44
    Challenges
    0.43
    椃
    0.43
    哐
    0.43
     Grenzen
    0.42
    POSITIVE LOGITS
     курса
    0.52
     officers
    0.49
    hello
    0.47
    ড়া
    0.47
    ho
    0.47
    ła
    0.46
    ığı
    0.46
    ai
    0.46
    pped
    0.46
     पद्धतीने
    0.46
    Activations Density 0.001%

    No Known Activations