© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36201
    Prev
    Next
    INDEX
    Explanations

    character creation

    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
     underestimated
    0.51
     impracticable
    0.51
    êmement
    0.51
    我觉得
    0.50
    אם
    0.48
    ك
    0.48
    ग़
    0.46
     이유
    0.46
     Interestingly
    0.46
    意義
    0.45
    POSITIVE LOGITS
    bolts
    0.46
    ments
    0.45
     supplies
    0.45
     with
    0.43
     shoe
    0.43
     tân
    0.42
     sp
    0.42
     shipping
    0.41
     ting
    0.40
     arc
    0.40
    Activations Density 0.009%

    No Known Activations