© 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. 80711
    Prev
    Next
    INDEX
    Explanations

    appear to be or seem

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

    presented as

    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
     `'
    0.49
     Но
    0.46
     ماده
    0.46
     ле
    0.45
     DNS
    0.44
     连接
    0.43
     Nası
    0.43
     `:`
    0.43
     Tallinn
    0.43
     көзге
    0.42
    POSITIVE LOGITS
     위한
    0.51
    unternehmen
    0.51
    campaign
    0.48
    planung
    0.48
    promote
    0.47
    roup
    0.45
     सहानु
    0.44
    gruppen
    0.44
    motivated
    0.43
    inductive
    0.43
    Activations Density 0.002%

    No Known Activations