© 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. 173164
    Prev
    Next
    INDEX
    Explanations

    child to her

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

    making analogies like this

    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
    0.48
    钻
    0.42
    士兵
    0.40
    Hamilton
    0.40
     staffing
    0.39
    笔
    0.39
     ब्राउन
    0.38
     পেন
    0.38
    Sticky
    0.38
    Allison
    0.38
    POSITIVE LOGITS
    ep
    0.57
     anguish
    0.55
     convulsions
    0.53
    দিগের
    0.50
     IComparable
    0.50
    торое
    0.49
    га
    0.48
    ’;
    0.48
    chaos
    0.48
    é
    0.48
    Activations Density 0.001%

    No Known Activations