© 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. 50631
    Prev
    Next
    INDEX
    Explanations

    physical attributes and concepts

    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
    ut
    0.53
    ↵↵
    0.51
    icul
    0.47
    ↵
    0.45
    ar
    0.44
    ot
    0.44
    R
    0.44
    rt
    0.44
    टी
    0.44
    us
    0.43
    POSITIVE LOGITS
     COMPANY
    0.45
     напол
    0.44
     אך
    0.42
     задачи
    0.40
     ज़िंदगी
    0.40
    それは
    0.39
     consejo
    0.39
     movilidad
    0.39
     ইত্যাদি
    0.39
    蜿
    0.39
    Activations Density 0.001%

    No Known Activations