© 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. 239139
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions and transitions

    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
    ༣
    0.48
     ควร
    0.47
     Конечно
    0.46
     എല്ലാം
    0.46
    ிருப்பது
    0.45
    这一切
    0.45
    )}}{\
    0.45
    るのは
    0.43
    當然
    0.42
    ﾊ
    0.42
    POSITIVE LOGITS
     During
    0.51
     during
    0.51
     When
    0.48
     In
    0.47
     when
    0.42
     two
    0.42
     जब
    0.42
     যখন
    0.42
     The
    0.41
     From
    0.41
    Activations Density 0.006%

    No Known Activations