© 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. 78690
    Prev
    Next
    INDEX
    Explanations

    step toward progress

    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
    如何在
    -0.88
     Gerichts
    -0.83
     výsled
    -0.81
    有著
    -0.81
     gdzie
    -0.79
     with
    -0.79
     attraverso
    -0.77
     mediante
    -0.77
    ecirc
    -0.76
    extern
    -0.75
    POSITIVE LOGITS
     forward
    2.22
    forward
    1.45
     toward
    1.45
     towards
    1.44
     FORWARD
    1.37
     in
    1.29
     Forward
    1.27
     forwards
    1.26
    Forward
    1.15
     backward
    1.13
    Activations Density 0.016%

    No Known Activations