© 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. 6685
    Prev
    Next
    INDEX
    Explanations

    reported by

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

    Russian model responses

    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
    ূনতম
    0.58
     curviliné
    0.55
    وزیشن
    0.54
     கரைச
    0.53
    蟶
    0.53
    體的
    0.52
    အစိတ်အပိုင်း
    0.52
     इनवर्स
    0.51
    劑
    0.51
     தனிநாயகம்
    0.50
    POSITIVE LOGITS
     "
    0.60
      
    0.59
     Б
    0.59
     З
    0.59
     К
    0.57
    <strong>
    0.57
     А
    0.57
     У
    0.57
    0.55
       
    0.55
    Activations Density 0.024%

    No Known Activations