© 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. 61385
    Prev
    Next
    INDEX
    Explanations

    developer tools, specific formatting

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

    escape characters or metacharacters

    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
    </
    0.56
    0.52
    begin
    0.51
     Indianapolis
    0.46
    x
    0.46
    时候
    0.45
    높
    0.45
     மாதம்
    0.44
     totaled
    0.43
     bilingual
    0.43
    POSITIVE LOGITS
    𝐛
    0.51
    煕
    0.49
    𝐠
    0.49
    𝐢
    0.46
     impurities
    0.46
    𝚐
    0.46
     işlemler
    0.44
     området
    0.43
    𝒋
    0.43
    কিছু
    0.43
    Activations Density 0.000%

    No Known Activations