© 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. 173092
    Prev
    Next
    INDEX
    Explanations

    medical attention, allowing, police, fighting, be nervous, do good, successful completion

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

    explaining why or how

    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
     extracts
    0.49
    ಮೇ
    0.49
     unexpectedly
    0.47
    なぜ
    0.47
     emits
    0.46
     menjelaskan
    0.45
     pons
    0.45
    お
    0.45
     where
    0.45
    Azer
    0.44
    POSITIVE LOGITS
    íf
    0.51
     الرغم
    0.46
     Morav
    0.45
     Davie
    0.45
     Dunbar
    0.44
    ężczy
    0.42
     ক্যারি
    0.42
    verde
    0.42
     paysage
    0.42
    
    0.42
    Activations Density 0.000%

    No Known Activations