© 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. 49322
    Prev
    Next
    INDEX
    Explanations

    actions and events

    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
    л
    0.58
    р
    0.52
    ل
    0.52
    те
    0.52
     обез
    0.51
    ز
    0.51
    лий
    0.49
    т
    0.49
    هل
    0.48
    ло
    0.47
    POSITIVE LOGITS
     grapple
    0.44
     ruptured
    0.43
     menampilkan
    0.42
     singkat
    0.41
     spiral
    0.41
    UnitTest
    0.41
     grappling
    0.41
    Encoded
    0.41
     parade
    0.40
    TextInput
    0.40
    Activations Density 0.008%

    No Known Activations