© 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. 7873
    Prev
    Next
    INDEX
    Explanations

    frequency varies

    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
     posticis
    0.50
     tsunami
    0.49
    ٹو
    0.48
     salivary
    0.48
     ۳
    0.47
     repre
    0.47
     localVarAccept
    0.47
     antibiotic
    0.46
    ⦖
    0.46
     bipartisan
    0.46
    POSITIVE LOGITS
    貨
    0.47
    狗
    0.45
    talent
    0.44
    裁
    0.43
    api
    0.43
    dao
    0.43
    wens
    0.42
    關
    0.42
    外部
    0.41
    棄
    0.41
    Activations Density 0.001%

    No Known Activations