© 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-262K
    7. 4763
    Prev
    Next
    INDEX
    Explanations

    language understanding capabilities

    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
    ಡುವುದ
    0.41
    נ
    0.40
     אחד
    0.40
    ܘܢ
    0.39
     fermeture
    0.38
    蹌
    0.38
     veggies
    0.37
     debilit
    0.37
    pport
    0.37
     einigen
    0.37
    POSITIVE LOGITS
     Analysis
    0.46
     Handbook
    0.44
     and
    0.42
     и
    0.41
    beliefs
    0.40
    罫
    0.40
     routinely
    0.40
    www
    0.39
     Computation
    0.39
    language
    0.39
    Activations Density 0.000%

    No Known Activations