© 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. 99804
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    knob, factory, orchestra, running

    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
    anganan
    0.49
     노래
    0.47
    nov
    0.43
     hospital
    0.43
    oc
    0.42
     union
    0.42
    anoate
    0.42
    ノ
    0.42
    PRO
    0.41
     cricket
    0.41
    POSITIVE LOGITS
     führ
    0.56
    公元
    0.51
    អំពី
    0.51
     Zustimmung
    0.49
     Prüfung
    0.49
    分數
    0.47
     Arce
    0.47
     رشد
    0.46
    的发展
    0.46
     Ignatius
    0.46
    Activations Density 0.000%

    No Known Activations