© 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. 236358
    Prev
    Next
    INDEX
    Explanations

    venue hire, URL, injury, decade

    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
    判定
    0.46
    setwd
    0.46
    سط
    0.45
    स्कर
    0.44
    }`);
    0.43
    海底
    0.43
    सू
    0.43
    )");
    0.42
    邈
    0.42
    सुक
    0.42
    POSITIVE LOGITS
     sínt
    0.52
    Ű
    0.52
     כ
    0.50
     زندگی
    0.50
     mén
    0.50
     év
    0.49
    Birds
    0.47
     molé
    0.47
     कान
    0.47
     pianta
    0.47
    Activations Density 0.000%

    No Known Activations