© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83052
    Prev
    Next
    INDEX
    Explanations

    We followed by action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     all
    -1.27
     several
    -1.05
    angkap
    -1.04
     armadura
    -0.99
     dirigir
    -0.97
     część
    -0.96
    organizer
    -0.95
     as
    -0.94
    Zdrav
    -0.93
    出發
    -0.91
    POSITIVE LOGITS
    "":
    1.09
    SizeMode
    1.01
    ଃ
    0.99
     levering
    0.96
    sorry
    0.96
    formerly
    0.96
     hebben
    0.95
     GOING
    0.94
    COE
    0.93
    PictureBox
    0.92
    Activations Density 0.034%

    No Known Activations