© 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. 36879
    Prev
    Next
    INDEX
    Explanations

    we use communication

    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
    内的
    0.50
    abhuto
    0.47
     datth
    0.45
    âncias
    0.44
    وٹی
    0.44
    鐒
    0.44
     htob
    0.42
    夂
    0.42
     pyrr
    0.42
     dechlorination
    0.41
    POSITIVE LOGITS
    on
    0.52
     viene
    0.48
     average
    0.47
     Existing
    0.46
    of
    0.45
    while
    0.45
    we
    0.44
     manage
    0.44
     sain
    0.43
    or
    0.43
    Activations Density 0.004%

    No Known Activations