© 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. 40607
    Prev
    Next
    INDEX
    Explanations

    punch above weight, punchy style

    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
    m
    1.65
    in
    1.63
    it
    1.54
    ac
    1.54
    س
    1.52
     a
    1.46
    ens
    1.45
    V
    1.41
    S
    1.41
    的产品
    1.38
    POSITIVE LOGITS
     ambito
    1.04
    ৫
    1.03
    й
    1.01
     hypothes
    0.98
     esterno
    0.97
    ем
    0.96
     forgo
    0.95
     reorgan
    0.95
    ικά
    0.94
     sacerdote
    0.93
    Activations Density 0.004%

    No Known Activations