© 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. 35802
    Prev
    Next
    INDEX
    Explanations

    admin password login

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

    your credential placeholders

    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
     활용
    0.52
    餐饮
    0.48
     Assets
    0.45
    setBadge
    0.44
    贩
    0.44
    ঞ্চল্য
    0.44
    传染
    0.43
     餐
    0.42
     दस्तावे
    0.42
    ItemLayout
    0.42
    POSITIVE LOGITS
    akka
    0.42
     K
    0.42
    sinh
    0.39
    0.39
    gamma
    0.38
    snake
    0.38
    np
    0.38
     M
    0.38
    fake
    0.37
    zak
    0.36
    Activations Density 0.003%

    No Known Activations