© 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. 58078
    Prev
    Next
    INDEX
    Explanations

    for [determiner/possessive] [noun context]

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

    this example

    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
     uve
    0.50
     داع
    0.47
     कहा
    0.45
    顕
    0.45
     viciss
    0.44
    鸿
    0.44
    悠
    0.43
    vivo
    0.42
    นาน
    0.42
    <0xEF>
    0.42
    POSITIVE LOGITS
    in
    0.64
    inę
    0.63
    ographiques
    0.55
    inud
    0.52
    咟
    0.52
    O
    0.51
     benötigt
    0.50
    Reward
    0.49
    inien
    0.49
    igste
    0.48
    Activations Density 0.026%

    No Known Activations