© 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. 23635
    Prev
    Next
    INDEX
    Explanations

    upper layer or overlay

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

    max Length, height, firstName, area

    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
     XNUMX
    0.45
    חים
    0.42
     sebagainya
    0.42
    等
    0.39
     ইত্যাদি
    0.39
    など
    0.38
     প্রমুখ
    0.38
    বিশ্ব
    0.38
    బు
    0.37
    গণের
    0.36
    POSITIVE LOGITS
     maupun
    0.70
     һәм
    0.45
     and
    0.44
     AND
    0.44
     illetve
    0.42
     Và
    0.41
     และ
    0.41
    지와
    0.41
    -,
    0.40
     mye
    0.40
    Activations Density 0.043%

    No Known Activations