© 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. 585
    Prev
    Next
    INDEX
    Explanations

    knowledge acquisition

    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
    자를
    0.40
     أي
    0.39
     своїх
    0.38
    솎
    0.38
    писы
    0.38
     chemokine
    0.38
     ње
    0.38
     shabd
    0.37
     সানডে
    0.37
     لأ
    0.37
    POSITIVE LOGITS
    et
    0.61
    r
    0.55
    m
    0.55
    v
    0.53
    que
    0.52
    in
    0.47
     que
    0.46
    V
    0.46
    ant
    0.45
    _
    0.45
    Activations Density 0.250%

    No Known Activations