© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23198
    Prev
    Next
    INDEX
    Explanations

    variable `d` in a loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     The
    0.38
     ,
    0.38
    The
    0.36
     alberga
    0.34
     Alder
    0.33
    Alder
    0.33
     cuart
    0.32
     Jean
    0.32
     Vier
    0.31
     Alpen
    0.31
    POSITIVE LOGITS
    ließlich
    0.40
    但在
    0.35
    但是在
    0.34
    뗄
    0.34
     непосред
    0.33
    噰
    0.33
    Ᏺ
    0.32
    ૭
    0.32
    ्रेसेस
    0.32
    𝒋
    0.32
    Activations Density 0.019%

    No Known Activations