© 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. 239013
    Prev
    Next
    INDEX
    Explanations

    kill switch context

    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
     farklı
    0.54
     दीवाना
    0.52
     duvar
    0.50
    nın
    0.48
     anlamına
    0.48
     eğ
    0.46
    觕
    0.46
     الجلد
    0.46
     وإ
    0.45
     फ्लाईओवर
    0.45
    POSITIVE LOGITS
    ज्ञ
    0.46
     négoci
    0.46
    喜
    0.44
    乎
    0.44
    合
    0.43
    野
    0.43
    꺾
    0.43
     memoranda
    0.42
    中に
    0.41
    협
    0.41
    Activations Density 0.001%

    No Known Activations