© 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. 31-GEMMASCOPE-2-RES-262K
    7. 5746
    Prev
    Next
    INDEX
    Explanations

    the start of phrases

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

    hello prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     هنتكلم
    0.41
     हैज
    0.41
    ものです
    0.36
     گزشتہ
    0.35
    죵
    0.35
     ।”
    0.35
     Gandhiji
    0.34
     ብዙውን
    0.33
     چھوٹے
    0.33
    这也是
    0.33
    POSITIVE LOGITS
    </h1>
    0.56
    </h2>
    0.38
    transit
    0.38
    R
    0.38
    V
    0.38
    D
    0.37
    G
    0.36
    B
    0.35
    and
    0.34
    cad
    0.34
    Activations Density 0.010%

    No Known Activations