© 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. 38313
    Prev
    Next
    INDEX
    Explanations

    see if / see how

    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
    ignée
    -1.16
     cosas
    -1.14
    pherals
    -1.11
    ächtig
    -1.05
     vouloir
    -1.01
    轳
    -0.99
    edade
    -0.98
     grava
    -0.98
    agrave
    -0.97
     チェア
    -0.97
    POSITIVE LOGITS
     if
    3.02
     what
    2.42
     how
    2.23
     where
    1.73
    if
    1.60
     whether
    1.53
     which
    1.50
     who
    1.41
     about
    1.30
    what
    1.25
    Activations Density 0.016%

    No Known Activations