© 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. 43585
    Prev
    Next
    INDEX
    Explanations

    on all fours

    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
    ע
    0.48
    ב
    0.46
    ש
    0.46
    İ
    0.45
    wilderness
    0.45
    లి
    0.44
    פ
    0.44
    ૦
    0.44
    ם
    0.43
    די
    0.43
    POSITIVE LOGITS
     }}^{\
    0.52
    gF
    0.45
     Kyi
    0.45
    .’’
    0.42
     Paglinawan
    0.42
     maneras
    0.41
    下一步
    0.41
    yo
    0.40
     ml
    0.39
    }}}{
    0.39
    Activations Density 0.006%

    No Known Activations