© 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-262K
    7. 9623
    Prev
    Next
    INDEX
    Explanations

    bin directory paths

    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_262k_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
    t
    1.49
     =
    1.05
    在
    1.03
    can
    0.98
    p
    0.98
    the
    0.96
    IANS
    0.95
    до
    0.93
    У
    0.90
    ﯼ
    0.90
    POSITIVE LOGITS
     bin
    1.13
    ний
    0.97
     Bin
    0.93
    bin
    0.93
     bruk
    0.88
     över
    0.86
     outro
    0.84
    il
    0.83
    ก
    0.83
     anden
    0.81
    Activations Density 0.017%

    No Known Activations