© 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. 107183
    Prev
    Next
    INDEX
    Explanations

    end boundary

    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
     by
    -1.10
     anyhow
    -0.87
     from
    -0.85
     with
    -0.84
     so
    -0.82
     for
    -0.80
    等等
    -0.79
     anyway
    -0.79
     after
    -0.78
     during
    -0.76
    POSITIVE LOGITS
     jusqu
    1.97
     hingga
    1.53
     até
    1.48
     hasta
    1.45
     až
    1.40
     sampai
    1.39
     تا
    1.38
     đến
    1.37
     עד
    1.36
     till
    1.30
    Activations Density 0.026%

    No Known Activations