© 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. 13410
    Prev
    Next
    INDEX
    Explanations

    wired.com stories

    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
    哴
    0.46
    appendTo
    0.42
     Ayn
    0.41
    文學
    0.41
     रहमान
    0.40
    粔
    0.39
    ربی
    0.39
    assian
    0.39
    洷
    0.38
     calcareous
    0.38
    POSITIVE LOGITS
     you
    0.48
    you
    0.47
    wire
    0.45
    wives
    0.44
    ti
    0.44
    You
    0.43
    wires
    0.43
    Chat
    0.43
    bandits
    0.43
     way
    0.42
    Activations Density 0.001%

    No Known Activations