© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 465
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by common conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite

    closing punctuation and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite

    )

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    0.64
     （
    0.61
    ر
    0.59
     to
    0.59
    <0x80>
    0.58
     (
    0.53
    ح
    0.52
    ר
    0.52
     be
    0.50
    AR
    0.45
    POSITIVE LOGITS
    u
    0.83
    a
    0.71
    i
    0.60
    z
    0.60
    ى
    0.58
    the
    0.57
    의
    0.57
    ే
    0.57
    ة
    0.54
    の
    0.51
    Activations Density 0.354%

    No Known Activations