© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73385
    Prev
    Next
    INDEX
    Explanations

    assessing qualities and performance

    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_22/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
     никогда
    -1.23
     that
    -1.18
    什么呢
    -1.14
    Never
    -1.04
    からは
    -1.02
     sodio
    -1.02
     Weisheit
    -1.00
    怎么做
    -0.98
    )/
    -0.97
    AILABLE
    -0.97
    POSITIVE LOGITS
     of
    3.11
    ability
    1.45
     and
    1.37
    8
    1.32
     whether
    1.20
     suitability
    1.14
    INA
    1.13
     \
    1.08
    sibility
    1.05
     acceptability
    1.02
    Activations Density 0.116%

    No Known Activations