© 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. 146353
    Prev
    Next
    INDEX
    Explanations

    travel casino destination status

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

    history examples

    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
    ды
    0.52
    𝔬
    0.51
    ēc
    0.50
    𝔱
    0.50
    тап
    0.48
    ibusdam
    0.48
    𝗲
    0.47
     elementos
    0.46
    전
    0.46
     enclose
    0.45
    POSITIVE LOGITS
    *((*
    0.47
    Entropy
    0.46
     জেড
    0.46
     покуп
    0.44
    Purchase
    0.44
     কিনে
    0.44
     XLS
    0.44
     फैक्टर
    0.44
    Sig
    0.43
     Phosph
    0.43
    Activations Density 0.000%

    No Known Activations