© 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. 57276
    Prev
    Next
    INDEX
    Explanations

    multi-word titles

    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
     only
    -1.31
     one
    -1.05
    While
    -0.96
     other
    -0.96
     while
    -0.93
     adds
    -0.91
    Both
    -0.88
     elde
    -0.87
    Only
    -0.87
     first
    -0.87
    POSITIVE LOGITS
    nessione
    1.11
     MSF
    1.03
     hahaha
    1.02
     totalement
    1.00
     VLC
    0.98
    iquest
    0.98
    TAI
    0.98
    ISSUE
    0.98
     TAI
    0.98
    BAC
    0.98
    Activations Density 0.001%

    No Known Activations