© 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. 104348
    Prev
    Next
    INDEX
    Explanations

    reading, how-to, lists

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

    special characters and programming syntax

    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
    warts
    0.48
    מיד
    0.45
    क्सर
    0.45
    總是
    0.44
    itale
    0.42
    獷
    0.41
    這是
    0.40
    ITC
    0.39
    ായത്
    0.39
    礪
    0.39
    POSITIVE LOGITS
    替换
    0.46
    }}>
    0.44
    之间
    0.42
     способы
    0.41
     断
    0.41
     элементы
    0.41
     arasındaki
    0.41
     পরস্পর
    0.41
    etzten
    0.41
    办法
    0.40
    Activations Density 0.001%

    No Known Activations