© 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. 25748
    Prev
    Next
    INDEX
    Explanations

    semi-permanent, Zero

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

    chatbot responds to phrases

    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
    평
    0.45
    Sne
    0.44
    Gordon
    0.43
    مق
    0.43
    zę
    0.42
    みが
    0.42
    اول
    0.41
     ห
    0.41
    빼
    0.40
    য
    0.40
    POSITIVE LOGITS
     drag
    0.53
     Drag
    0.47
     ध्वस्त
    0.47
     Jahr
    0.46
     कार्यवाही
    0.46
    ोजा
    0.45
    都會
    0.45
     banking
    0.44
    aturan
    0.44
     Cowboys
    0.44
    Activations Density 0.000%

    No Known Activations