© 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. 1678
    Prev
    Next
    INDEX
    Explanations

    conditional, temporal, and causal clauses

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

    introducing clauses

    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
     ឬ
    0.29
     ACTIVITIES
    0.29
     sechs
    0.28
     Nếu
    0.27
    GENER
    0.27
     Eğer
    0.27
    给
    0.26
    ੩
    0.26
     oder
    0.26
     WIDTH
    0.26
    POSITIVE LOGITS
     they
    0.35
     it
    0.34
    дони
    0.30
     তারা
    0.28
     theyre
    0.28
     he
    0.28
     вони
    0.27
    soever
    0.26
     они
    0.25
     there
    0.24
    Activations Density 0.355%

    No Known Activations