© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29057
    Prev
    Next
    INDEX
    Explanations

    exceptions, skills, attributes

    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_65k_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
     appellees
    0.44
    ㎖
    0.44
    స్ట్రీ
    0.44
    ӣ
    0.43
    㿝
    0.43
     ப்ளாக்
    0.43
     swipe
    0.42
    ओम
    0.41
     swipes
    0.41
    ︶
    0.40
    POSITIVE LOGITS
     Country
    0.41
     Connolly
    0.38
    lovl
    0.38
    achricht
    0.38
     betreff
    0.37
     समान
    0.37
    max
    0.36
     jeweils
    0.36
    0.36
    授
    0.36
    Activations Density 0.001%

    No Known Activations