© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3098
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    তীশ
    0.49
    హిత
    0.49
     cut
    0.48
    Cut
    0.46
    切
    0.45
     切
    0.45
    ut
    0.44
     Cut
    0.44
    Cutting
    0.42
     Cutting
    0.41
    POSITIVE LOGITS
    けば
    0.47
    สอง
    0.45
    ի
    0.42
    ]*
    0.42
    adeon
    0.42
     respectively
    0.41
    phere
    0.41
    પ
    0.41
    それぞれ
    0.41
    дио
    0.41
    Activations Density 0.030%

    No Known Activations