© 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. 204978
    Prev
    Next
    INDEX
    Explanations

    outstanding achievement

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

    Space, SpaceX, space exploration

    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
    极端
    0.52
     znajdu
    0.52
    و
    0.50
     apunta
    0.48
    늙
    0.46
     вероятно
    0.46
    环境变量
    0.45
    ेटिव
    0.44
    Thu
    0.44
     thu
    0.44
    POSITIVE LOGITS
     uniformity
    0.50
    falen
    0.47
     ihren
    0.47
     &.
    0.45
    usi
    0.43
     Minuten
    0.42
     名
    0.42
    (;
    0.42
     Seiten
    0.42
    ahren
    0.42
    Activations Density 0.000%

    No Known Activations