© 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. 36125
    Prev
    Next
    INDEX
    Explanations

    choosing land landings accidents

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

    communist monkey, discovered life, securities, clustered

    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
    <0x9B>
    0.52
     نجم
    0.49
    を見る
    0.48
     স্যাম
    0.46
     것으로
    0.46
    ｚ
    0.45
    規
    0.45
    ｩ
    0.44
    恪
    0.43
    isenberg
    0.43
    POSITIVE LOGITS
    身材
    0.50
    waarden
    0.48
     animale
    0.48
    adakan
    0.48
     landings
    0.47
     Pues
    0.46
     endophytic
    0.46
    Nombre
    0.46
    由于
    0.45
    nombre
    0.45
    Activations Density 0.000%

    No Known Activations