© 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. 59998
    Prev
    Next
    INDEX
    Explanations

    where door

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

    logical structure expressions

    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
     మై
    0.45
     బాధ
    0.45
     Saying
    0.43
     질
    0.42
     الري
    0.42
     गिनती
    0.42
    莧
    0.42
    సె
    0.41
    吳
    0.41
     영향
    0.41
    POSITIVE LOGITS
     preservatives
    0.59
    હાસ
    0.52
    lcc
    0.50
    uje
    0.50
     protection
    0.49
    ném
    0.49
    onic
    0.48
     fraudsters
    0.48
    oram
    0.47
    '
    0.47
    Activations Density 0.000%

    No Known Activations