© 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. 108642
    Prev
    Next
    INDEX
    Explanations

    bit shifting operators

    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
    <table>
    -0.91
     fhort
    -0.81
     מדי
    -0.81
     firft
    -0.80
     fhould
    -0.79
    ‹
    -0.79
    isierung
    -0.77
     riport
    -0.77
     pleaf
    -0.76
     REQUIRED
    -0.75
    POSITIVE LOGITS
     >>
    2.28
    >>
    1.80
     >>=
    1.55
    )>>
    1.25
    >>,
    1.16
     >>>
    1.15
     shr
    1.13
     right
    1.04
    shr
    1.03
    >>;
    0.95
    Activations Density 0.016%

    No Known Activations