© 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. 117228
    Prev
    Next
    INDEX
    Explanations

    formal closing remarks

    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
    Cheers
    -1.02
     Cheers
    -0.83
    Plasmid
    -0.81
     $-$
    -0.78
     到
    -0.77
    odenal
    -0.76
     cheered
    -0.76
    我也
    -0.76
     mandibular
    -0.76
     cheerful
    -0.74
    POSITIVE LOGITS
    Respectfully
    1.67
     respectfully
    1.66
     Respectfully
    1.48
    yours
    1.17
     respectful
    1.13
     yours
    1.10
    respect
    1.05
    Yours
    1.02
     submitted
    1.01
     obedient
    0.98
    Activations Density 0.012%

    No Known Activations