© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56787
    Prev
    Next
    INDEX
    Explanations

    variation between

    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
    Đ
    0.47
    thet
    0.44
    Gu
    0.43
    コ
    0.42
    Lif
    0.40
    Land
    0.39
    Т
    0.39
    VS
    0.38
    Ка
    0.38
    lif
    0.38
    POSITIVE LOGITS
     prêts
    0.49
     Eisenhower
    0.47
     Ethiopian
    0.44
     Cauchy
    0.43
     semi
    0.42
     Outcome
    0.42
     Meanwhile
    0.42
     Prague
    0.42
     Jordanian
    0.41
     Euclidean
    0.41
    Activations Density 0.007%

    No Known Activations