© 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. 16-GEMMASCOPE-2-RES-65K
    7. 154
    Prev
    Next
    INDEX
    Explanations

    referencing specific instances

    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_16_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
    u
    0.48
    т
    0.46
    at
    0.44
    on
    0.43
    x
    0.41
    y
    0.41
    uix
    0.38
    н
    0.38
     Leverage
    0.37
    埬
    0.37
    POSITIVE LOGITS
    .
    0.55
     as
    0.51
    この
    0.44
     этого
    0.39
    。
    0.39
     это
    0.38
     kaleidoscopic
    0.37
     এই
    0.37
     dieses
    0.37
    这里
    0.37
    Activations Density 0.737%

    No Known Activations