© 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. 217670
    Prev
    Next
    INDEX
    Explanations

    business days

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

    sequence of words following certain keywords

    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
    Prep
    0.46
     Feet
    0.40
     Mother
    0.40
     CPD
    0.40
     glandular
    0.39
     Prep
    0.39
     NAD
    0.39
    :
    0.38
     Bigger
    0.38
     VB
    0.38
    POSITIVE LOGITS
    敉
    0.52
    メガネ
    0.50
     stockholder
    0.49
    歐
    0.49
    сні
    0.48
    σταν
    0.48
    囷
    0.48
    сков
    0.48
     magasins
    0.47
     unprofitable
    0.47
    Activations Density 0.000%

    No Known Activations