© 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. 112776
    Prev
    Next
    INDEX
    Explanations

    species, photography, performance

    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
    不做
    0.41
     distinguishes
    0.40
     virtually
    0.40
    麃
    0.40
    ုံး
    0.39
    洿
    0.39
    热闹
    0.38
    े
    0.38
    黾
    0.38
     distinguishing
    0.37
    POSITIVE LOGITS
    ne
    0.54
     przyj
    0.49
    te
    0.49
     voller
    0.49
     ingred
    0.48
    aine
    0.46
     stwor
    0.46
    aring
    0.45
    alle
    0.45
     Estatal
    0.45
    Activations Density 0.001%

    No Known Activations