© 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. 217264
    Prev
    Next
    INDEX
    Explanations

    impressive superlatives or metrics

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

    little bit ridiculous

    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
    고
    0.44
    贱
    0.43
    รรม
    0.42
    ว่า
    0.42
     unbiased
    0.41
    지고
    0.41
     আপনা
    0.40
     generalizations
    0.40
    า
    0.40
     Method
    0.40
    POSITIVE LOGITS
     sorprendente
    0.58
     sorprend
    0.57
     zask
    0.55
     exhilarating
    0.53
     spectacularly
    0.52
     astonishing
    0.50
    shareButton
    0.49
     strikingly
    0.48
     surprising
    0.47
     deliciously
    0.46
    Activations Density 0.001%

    No Known Activations