© 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-16K
    7. 4474
    Prev
    Next
    INDEX
    Explanations

    data structure names

    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_16k_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
     dozens
    0.31
     the
    0.31
    id
    0.30
     which
    0.30
     yarg
    0.29
     &(
    0.29
     życiu
    0.29
    5
    0.29
    credits
    0.29
    ↵
    0.28
    POSITIVE LOGITS
     phosphatase
    0.33
    ําน
    0.32
     مثال
    0.32
    MaskInto
    0.31
    𒆳
    0.31
    ํา
    0.30
     Ehren
    0.30
     काही
    0.30
     سب
    0.30
    Adams
    0.30
    Activations Density 0.117%

    No Known Activations