© 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. 164235
    Prev
    Next
    INDEX
    Explanations

    in the context of conditional clauses

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

    growth and expansion

    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
     بودم
    0.54
     junkie
    0.51
     neki
    0.49
    讨厌
    0.48
     કંઈ
    0.48
    谗
    0.47
     notizia
    0.46
    だったら
    0.46
     journaliste
    0.46
    机票
    0.45
    POSITIVE LOGITS
     \
    0.53
    synchronized
    0.52
     matures
    0.52
     patterning
    0.52
     mimics
    0.50
    {{\
    0.48
     are
    0.48
    paired
    0.48
     extends
    0.47
     coupled
    0.47
    Activations Density 0.000%

    No Known Activations