© 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. 387
    Prev
    Next
    INDEX
    Explanations

    protein and aggregates

    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
    嫨
    0.59
     convin
    0.56
    중에
    0.55
    !।
    0.53
     calm
    0.52
    つき
    0.52
    ங்கள
    0.51
    인이
    0.51
    능
    0.51
     Chebyshev
    0.50
    POSITIVE LOGITS
    ur
    0.64
    3
    0.59
    ing
    0.57
    ut
    0.56
    ya
    0.55
    4
    0.55
    1
    0.54
    9
    0.53
    va
    0.52
    na
    0.52
    Activations Density 0.000%

    No Known Activations