© 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. 188906
    Prev
    Next
    INDEX
    Explanations

    earwax

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

    interpretations and confusion

    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
     a
    0.53
    Core
    0.51
    P
    0.51
    एस
    0.49
    numero
    0.46
    Interactor
    0.46
    bacteria
    0.45
    Recognition
    0.44
    Ip
    0.44
     pangan
    0.44
    POSITIVE LOGITS
     Amtrak
    0.53
    軫
    0.48
    밂
    0.47
     AVE
    0.47
    <unused30>
    0.46
     ব্যায়াম
    0.45
     JAG
    0.44
     Angry
    0.43
     GATT
    0.43
     Oktoberfest
    0.43
    Activations Density 0.000%

    No Known Activations