© 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. 64080
    Prev
    Next
    INDEX
    Explanations

    making judgments

    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
    optarg
    -0.87
     explic
    -0.84
     explica
    -0.84
     эн
    -0.83
     disputa
    -0.82
     persuasive
    -0.81
     SD
    -0.79
    чивать
    -0.79
     Opt
    -0.78
     PROPOS
    -0.78
    POSITIVE LOGITS
     judgment
    3.34
     judge
    3.23
     judgement
    3.20
     judgments
    3.06
     judged
    3.03
     judging
    3.00
     judgements
    2.89
    judgment
    2.83
    judge
    2.78
    jud
    2.56
    Activations Density 0.043%

    No Known Activations