© 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. 195473
    Prev
    Next
    INDEX
    Explanations

    expressions of need

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

    want/need/meaning

    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
    p
    0.49
    potentially
    0.46
    apm
    0.45
    ap
    0.45
    apit
    0.45
    alp
    0.45
    mpl
    0.44
    aysia
    0.43
    aph
    0.42
    uste
    0.41
    POSITIVE LOGITS
    ܠ
    0.47
     长
    0.46
     Иногда
    0.46
     两
    0.45
     гиб
    0.45
     时间
    0.42
     rychle
    0.42
     często
    0.41
     കൃ
    0.41
    䉍
    0.41
    Activations Density 0.090%

    No Known Activations