© 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. 50576
    Prev
    Next
    INDEX
    Explanations

    most words

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

    economic conditions or descriptions

    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
     n
    0.47
     .
    0.47
     Routed
    0.46
    ponse
    0.43
     الص
    0.43
    <
    0.42
     T
    0.42
    一只
    0.42
    ä
    0.42
    wn
    0.42
    POSITIVE LOGITS
    まあ
    0.57
    ίου
    0.52
     まあ
    0.50
    のための
    0.49
     โอ้
    0.48
    ेडियम
    0.48
    <unused3>
    0.48
     नाते
    0.47
    ர்ஸ்
    0.47
    <unused94>
    0.47
    Activations Density 0.000%

    No Known Activations