© 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. 42804
    Prev
    Next
    INDEX
    Explanations

    it is / it has

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

    I am/it is

    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
    whenever
    0.35
     Whenever
    0.34
     ಯಾವಾಗ
    0.33
     பெய
    0.32
     그러나
    0.32
    どのような
    0.32
    𝗢
    0.31
     யாரும்
    0.31
    𝒍
    0.31
     இதை
    0.30
    POSITIVE LOGITS
     is
    0.37
     đang
    0.37
     has
    0.34
     está
    0.32
     was
    0.31
     està
    0.31
     hanno
    0.31
     yaptık
    0.30
     đã
    0.30
     están
    0.29
    Activations Density 0.280%

    No Known Activations