© 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. 117621
    Prev
    Next
    INDEX
    Explanations

    Grindon Hall, Stonyx, AC ACCC

    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
     there
    -1.09
     only
    -1.03
     even
    -0.91
     which
    -0.88
     apparently
    -0.84
     both
    -0.84
     aligned
    -0.82
     probably
    -0.81
     where
    -0.81
     Traité
    -0.80
    POSITIVE LOGITS
    比较
    0.94
    .*")]
    0.92
    ちょっと
    0.92
    ㎍
    0.91
    tigem
    0.91
    wning
    0.88
    Hay
    0.88
    "},
    0.86
    Sú
    0.86
     Rom
    0.85
    Activations Density 0.062%

    No Known Activations