© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 69268
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs and common phrases

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

    constantly generating predictions

    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
     campagnes
    0.47
     années
    0.47
     photographie
    0.47
     noviembre
    0.46
    ษ
    0.46
    tembre
    0.46
     vínculos
    0.46
     letech
    0.46
    ਮ
    0.45
    이스
    0.44
    POSITIVE LOGITS
     VMware
    0.61
    load
    0.60
     load
    0.52
     GMC
    0.50
    身为
    0.50
     Load
    0.50
     to
    0.49
    vm
    0.49
    0
    0.49
    Config
    0.49
    Activations Density 0.001%

    No Known Activations