© 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. 209381
    Prev
    Next
    INDEX
    Explanations

    exclusive

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

    breakdown listing

    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
    FAKE
    0.58
     esse
    0.50
    ਦ
    0.50
    hite
    0.48
    ين
    0.48
    ejs
    0.48
    বিদ্যা
    0.48
    c
    0.48
    lineWidth
    0.47
    రీలు
    0.47
    POSITIVE LOGITS
    ,
    0.47
    *
    0.46
     valet
    0.45
     aproxim
    0.44
     exacerb
    0.44
    \
    0.43
     approxim
    0.43
     maksimum
    0.40
    isier
    0.40
     aggravating
    0.39
    Activations Density 0.001%

    No Known Activations