© 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. 8921
    Prev
    Next
    INDEX
    Explanations

    conjunctions after commas

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

    contrasting conjunctions

    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
    Ῥ
    0.46
    jų
    0.43
    ília
    0.42
     empate
    0.40
     पेशेवरों
    0.40
    Ī
    0.40
     innego
    0.39
     mínimos
    0.39
    ラー
    0.38
    جموعة
    0.38
    POSITIVE LOGITS
     although
    0.59
     Although
    0.50
     aunque
    0.49
    although
    0.49
     with
    0.48
     cypress
    0.46
    aunque
    0.46
     but
    0.45
     especially
    0.44
     i
    0.44
    Activations Density 0.048%

    No Known Activations