© 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. 75320
    Prev
    Next
    INDEX
    Explanations

    world, extracellular, highlights, urgency

    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
     ==
    0.48
    初心者
    0.46
     =
    0.43
     AND
    0.42
    :
    0.42
    ouer
    0.41
    oraus
    0.41
    わからない
    0.40
    当然
    0.40
    ,
    0.39
    POSITIVE LOGITS
     efectu
    0.48
     publicidad
    0.44
     conductas
    0.44
     metabolite
    0.40
    зви
    0.40
     পুনরায়
    0.40
     ተጨማሪ
    0.40
     hogi
    0.40
     childrens
    0.39
     trasmissione
    0.39
    Activations Density 0.009%

    No Known Activations