© 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. 121876
    Prev
    Next
    INDEX
    Explanations

    consider, tally, servicing, trial, cycle

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

    Information and preparation

    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
    incent
    0.49
    gly
    0.46
    allow
    0.42
     employers
    0.41
    hose
    0.41
     incentivize
    0.41
    用語
    0.40
    劃
    0.40
     shine
    0.40
     lockers
    0.39
    POSITIVE LOGITS
     createArticle
    0.47
    ικής
    0.47
    τικής
    0.46
    പ്പെട്ടു
    0.46
     odw
    0.45
    OGND
    0.45
    鼗
    0.44
     रियर
    0.44
     countDown
    0.43
    ാർ
    0.43
    Activations Density 0.001%

    No Known Activations