© 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. 10-GEMMASCOPE-RES-131K
    7. 7680
    Prev
    Next
    INDEX
    Explanations

    protocol

    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_10/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
     but
    -1.84
     que
    -1.51
    ，，
    -1.48
    笮
    -1.48
    哟
    -1.48
    ⼥
    -1.43
    ࿙
    -1.42
    </strong>
    -1.39
     fashioned
    -1.38
     horizontally
    -1.34
    POSITIVE LOGITS
    asanjo
    1.76
    
    1.72
     SUCH
    1.70
     BOTH
    1.69
    】:
    1.66
     },
    1.61
     aqueles
    1.59
    ﻂ
    1.59
     üblichen
    1.55
     THOSE
    1.54
    Activations Density 0.017%

    No Known Activations