© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10159
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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_40_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
    いくつか
    0.45
     şöyle
    0.44
    Several
    0.44
     विशेषताएं
    0.42
     몇
    0.42
     いく
    0.42
     Several
    0.41
    几
    0.41
     several
    0.40
     rests
    0.40
    POSITIVE LOGITS
    known
    0.51
    labelled
    0.49
     hailing
    0.49
     requiring
    0.48
    backed
    0.47
     favoured
    0.47
    Situated
    0.47
    located
    0.47
    Known
    0.47
     located
    0.46
    Activations Density 0.138%

    No Known Activations