© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64098
    Prev
    Next
    INDEX
    Explanations

    transition to a new state

    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
     remaining
    -1.05
    鈷
    -0.97
     kehamilan
    -0.97
    waiting
    -0.96
    好評
    -0.96
     sobrevi
    -0.96
    zości
    -0.93
    櫛
    -0.93
    return
    -0.92
    があり
    -0.91
    POSITIVE LOGITS
     involved
    1.37
     aware
    1.37
     acquainted
    1.30
     convinced
    1.16
     friends
    1.10
     a
    1.06
     accustomed
    1.06
     enam
    1.00
     Freunde
    1.00
     maggio
    0.99
    Activations Density 0.022%

    No Known Activations