© 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. 20109
    Prev
    Next
    INDEX
    Explanations

    first name followed by initial

    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
    ъек
    0.70
    ଈ
    0.70
    ൨
    0.68
    ২৩
    0.67
    Macrophages
    0.66
    ৬০
    0.66
    Ꮔ
    0.66
    <unused368>
    0.66
    zechoslovakia
    0.65
    vrdr
    0.65
    POSITIVE LOGITS
     J
    1.20
     C
    1.07
     D
    1.06
     S
    1.02
     G
    1.02
     T
    1.00
     R
    0.97
     M
    0.95
     L
    0.95
     A
    0.94
    Activations Density 0.000%

    No Known Activations