© 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. 194691
    Prev
    Next
    INDEX
    Explanations

    software, new releases, solutions

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

    platforms and frameworks

    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
    閣
    0.44
    濰
    0.44
    azen
    0.42
    фото
    0.41
     brood
    0.40
    棪
    0.40
    妝
    0.40
    輻
    0.40
    utum
    0.39
    髹
    0.39
    POSITIVE LOGITS
     võimal
    0.48
     gennem
    0.46
     mulighed
    0.45
    اری
    0.45
    newInstance
    0.45
     وی
    0.44
     حیر
    0.44
     测试
    0.43
     টেস্ট
    0.43
     deterg
    0.42
    Activations Density 0.001%

    No Known Activations