© 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. 127993
    Prev
    Next
    INDEX
    Explanations

    Destination or delivery point

    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
    Balancer
    0.50
    اري
    0.48
    ر
    0.47
    র্ষ
    0.46
    策划
    0.46
    ృత
    0.45
    رس
    0.45
    铡
    0.44
    ستون
    0.44
    يان
    0.44
    POSITIVE LOGITS
     alluvial
    0.54
    land
    0.49
     hva
    0.48
     inland
    0.47
     behov
    0.47
     fleste
    0.46
     गरीब
    0.46
     intestate
    0.46
     kø
    0.45
     Ethiopia
    0.45
    Activations Density 0.008%

    No Known Activations