© 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. 210769
    Prev
    Next
    INDEX
    Explanations

    metal foil, simply text

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

    Public Key Infrastructure

    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
     보호
    0.46
    ennem
    0.46
     %),
    0.45
     facteur
    0.45
     asphy
    0.43
     adipis
    0.42
     показатель
    0.42
     éto
    0.42
    퐁
    0.42
    구성
    0.42
    POSITIVE LOGITS
    ated
    0.52
    ą
    0.48
    BufOffset
    0.46
     Merchants
    0.45
    ie
    0.45
     Maine
    0.44
    ى
    0.44
    eme
    0.43
    rated
    0.42
     মোটামুটি
    0.41
    Activations Density 0.001%

    No Known Activations