© 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. 87744
    Prev
    Next
    INDEX
    Explanations

    electrical sockets

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

    biological perspective, socket if, score

    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
    ott
    0.48
    (\
    0.48
    一
    0.46
    ếc
    0.46
    <0xE7>
    0.45
    ch
    0.45
    <0xE9>
    0.45
    V
    0.44
    হ
    0.44
    B
    0.43
    POSITIVE LOGITS
     conlle
    0.49
     pretext
    0.48
     predominate
    0.48
     sejak
    0.47
     comunicarse
    0.47
     empec
    0.46
     गाइस
    0.46
     micrófono
    0.45
     สืบค้นเมื่อ
    0.45
     rekomend
    0.45
    Activations Density 0.006%

    No Known Activations