© 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. 136499
    Prev
    Next
    INDEX
    Explanations

    various products and actions

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

    umbrella industry, client expertise, concentration varies

    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
    椥
    0.49
    有时候
    0.48
    一种
    0.47
    一起
    0.46
    抱着
    0.46
    vard
    0.45
     सूचीबद्ध
    0.45
    că
    0.44
    GRADE
    0.44
    ژگی
    0.43
    POSITIVE LOGITS
     potente
    0.47
     Starter
    0.46
     zweiten
    0.45
    ఔ
    0.45
     Einst
    0.45
    ør
    0.44
    ಕರ
    0.44
     secondi
    0.44
     पांव
    0.44
    ekra
    0.42
    Activations Density 0.001%

    No Known Activations