© 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. 116054
    Prev
    Next
    INDEX
    Explanations

    choosing one over another

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

    defining planets, understanding concepts, comparing items

    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
     ephemeral
    0.47
     dui
    0.47
     ulterior
    0.46
    preparing
    0.46
    nid
    0.45
    noti
    0.44
    </code>
    0.43
    𝗬
    0.43
     epiphany
    0.42
    wrist
    0.42
    POSITIVE LOGITS
    ทาง
    0.51
    และ
    0.50
     หลัก
    0.49
    和社会
    0.48
    和他
    0.47
     dhatu
    0.47
    枧
    0.46
    วาม
    0.46
    మాట
    0.45
     เขา
    0.45
    Activations Density 0.000%

    No Known Activations