© 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. 54531
    Prev
    Next
    INDEX
    Explanations

    Tiber, Jasper, himself, EMA, STAN

    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
     ফার্ম
    0.48
    هم
    0.42
     وهي
    0.41
    2
    0.41
     Nov
    0.40
    hopper
    0.39
    are
    0.38
    اتي
    0.38
     Admission
    0.38
    ati
    0.38
    POSITIVE LOGITS
     比
    0.61
    폿
    0.52
     전투
    0.48
    ruzione
    0.47
     に対して
    0.47
    纂
    0.47
    쫒
    0.47
    ま
    0.47
    Ւ
    0.46
    뷊
    0.46
    Activations Density 0.012%

    No Known Activations