© 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. 70287
    Prev
    Next
    INDEX
    Explanations

    common words followed by varied items

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

    emotion, consequence, importance, trust, details

    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
     canciones
    0.53
     fieles
    0.53
     $
    0.48
     ll
    0.47
     ação
    0.47
     EL
    0.47
     কয়েকজন
    0.46
     faithful
    0.45
     confirmó
    0.45
     ভালোবাসি
    0.44
    POSITIVE LOGITS
    The
    0.53
    the
    0.51
     suppuration
    0.50
    Ꮼ
    0.50
    Akt
    0.50
     питань
    0.48
    Rate
    0.48
    ૩
    0.48
     хотелось
    0.47
    Misc
    0.47
    Activations Density 0.000%

    No Known Activations