© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 228428
    Prev
    Next
    INDEX
    Explanations

    our followed by system or website

    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
    朼
    0.58
    कांग्रेस
    0.57
     preside
    0.57
     cultivate
    0.55
     تجارت
    0.52
     समझा
    0.52
    を入れて
    0.52
    TAP
    0.52
     obsług
    0.51
     construe
    0.51
    POSITIVE LOGITS
    но
    0.50
    εν
    0.49
    к
    0.48
    rolls
    0.42
     Patel
    0.42
    аз
    0.42
    nessy
    0.40
    و
    0.40
    эн
    0.40
     kes
    0.39
    Activations Density 0.000%

    No Known Activations