© 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. 28908
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
     (>
    0.45
     ብዙውን
    0.44
     অবশ্য
    0.44
    ₁(
    0.42
     (§
    0.41
     temperament
    0.41
     capacités
    0.41
     congruent
    0.40
    ുവരി
    0.40
    ແ
    0.40
    POSITIVE LOGITS
     with
    0.62
     to
    0.59
     as
    0.54
     for
    0.54
     an
    0.53
    with
    0.52
    아
    0.50
    5
    0.50
    have
    0.48
     khi
    0.48
    Activations Density 0.088%

    No Known Activations