© 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. 46439
    Prev
    Next
    INDEX
    Explanations

    define integer variable

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

    pregnant women

    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
     عند
    0.52
     سال
    0.49
     коло
    0.46
     ಸ
    0.45
     روز
    0.45
     Republic
    0.43
     پو
    0.42
     روش
    0.42
     پڑھ
    0.42
    糞
    0.42
    POSITIVE LOGITS
    因此
    0.52
    性价比
    0.49
     erzählen
    0.48
    因而
    0.47
    主教
    0.45
    编写
    0.45
     হওয়ায়
    0.45
    सेप्शन
    0.44
     permettent
    0.44
    藠
    0.44
    Activations Density 0.000%

    No Known Activations