© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76848
    Prev
    Next
    INDEX
    Explanations

    introducing a reason

    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
     väldigt
    -1.06
     nästan
    -1.04
     assez
    -1.03
     sjuk
    -1.02
     particulier
    -1.02
     able
    -1.01
    atization
    -1.00
    teps
    -0.99
    icestershire
    -0.99
    tocks
    -0.97
    POSITIVE LOGITS
     of
    2.48
     if
    2.08
     it
    1.91
     frankly
    1.83
     who
    1.63
     believe
    1.44
     why
    1.42
     honestly
    1.41
     when
    1.34
    いかがでしたか
    1.34
    Activations Density 0.022%

    No Known Activations