© 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. 216863
    Prev
    Next
    INDEX
    Explanations

    `you should` `right now` `marry into`

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

    names of things with specific meanings

    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
     ज़कात
    0.50
     SQUARE
    0.48
    Ｌ
    0.48
    ڕۆ
    0.47
    じ
    0.46
    वाह
    0.46
     LITERATURE
    0.46
    <h3>
    0.46
    わた
    0.45
    ث
    0.45
    POSITIVE LOGITS
     initio
    0.50
     commander
    0.46
     ministers
    0.45
     commanders
    0.42
     bewegen
    0.42
     fared
    0.42
     screened
    0.42
     পক্ষে
    0.41
    zę
    0.41
    avgs
    0.40
    Activations Density 0.001%

    No Known Activations