© 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. 79083
    Prev
    Next
    INDEX
    Explanations

    keeping costs down

    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
     Crit
    -0.85
    FunctionType
    -0.83
     melk
    -0.83
    ılık
    -0.80
    WireFormatLite
    -0.79
    trina
    -0.78
    Sø
    -0.77
    רון
    -0.76
    ná
    -0.76
     Louie
    -0.75
    POSITIVE LOGITS
     control
    2.34
    控制
    2.28
     controlling
    2.09
    Controlling
    1.98
     keep
    1.92
     Controlling
    1.91
    control
    1.91
     Control
    1.88
     kept
    1.85
     keeping
    1.77
    Activations Density 0.057%

    No Known Activations