© 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. 233920
    Prev
    Next
    INDEX
    Explanations

    space, record

    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
    醾
    0.59
    姮
    0.57
    沨
    0.55
    鹖
    0.54
     निवेशक
    0.54
     नियोक्ता
    0.53
    Investors
    0.53
    嚧
    0.53
    来了
    0.52
     निवेशकों
    0.52
    POSITIVE LOGITS
    ↵
    0.67
    <0x0D>
    0.57
     monochrome
    0.55
     stored
    0.52
    0.52
     D
    0.52
     scrib
    0.52
     F
    0.51
     d
    0.51
    h
    0.51
    Activations Density 0.000%

    No Known Activations