© 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. 50037
    Prev
    Next
    INDEX
    Explanations

    extra complexity

    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
    ুল্য
    0.47
    aparikkh
    0.46
     हृदय
    0.44
    从此
    0.43
    赃
    0.42
     {}>,
    0.42
     trì
    0.42
     clinique
    0.42
     levens
    0.41
    itabbam
    0.41
    POSITIVE LOGITS
     resistance
    0.45
     Q
    0.44
     better
    0.42
     on
    0.42
     comparatively
    0.42
     simulation
    0.41
     بهتر
    0.41
     expediency
    0.41
    0.41
     relatively
    0.40
    Activations Density 0.010%

    No Known Activations