© 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. 229242
    Prev
    Next
    INDEX
    Explanations

    thing inside

    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
    TestingModule
    0.49
    い
    0.47
    ༘
    0.47
    ান
    0.46
    英文
    0.45
    บริเวณ
    0.45
    ኽ
    0.45
    无法
    0.44
    ம்
    0.44
    英语
    0.43
    POSITIVE LOGITS
     atlet
    0.48
     plumbers
    0.48
     Salts
    0.46
     propried
    0.45
     Çünkü
    0.45
     PKC
    0.44
     miners
    0.44
     lama
    0.44
     costru
    0.43
     porque
    0.42
    Activations Density 0.000%

    No Known Activations