© 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. 33181
    Prev
    Next
    INDEX
    Explanations

    companion

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

    version numbers or times

    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
     มิถุนายน
    0.30
     ゲーム
    0.27
     nikdy
    0.27
     ഭക്ഷണ
    0.27
     中
    0.26
     היום
    0.26
    堺
    0.26
     swoich
    0.26
     способствует
    0.26
     वाकई
    0.25
    POSITIVE LOGITS
     companion
    0.32
    idez
    0.32
    ileges
    0.31
    ኾ
    0.31
    дам
    0.31
     Companion
    0.31
    iles
    0.30
    iful
    0.30
    eria
    0.30
    хів
    0.30
    Activations Density 0.035%

    No Known Activations