© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95574
    Prev
    Next
    INDEX
    Explanations

    however introducing contrast

    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
    providedIn
    -2.00
     and
    -1.82
     it
    -1.58
    嘁
    -1.51
     jugé
    -1.45
    ၅
    -1.45
    过后
    -1.43
     Forscher
    -1.41
    たまたま
    -1.41
    toDouble
    -1.40
    POSITIVE LOGITS
    0
    2.23
    ,
    2.22
    6
    2.03
    4
    2.03
    3
    1.79
    1
    1.79
    5
    1.78
    '
    1.73
    7
    1.71
    2
    1.63
    Activations Density 0.020%

    No Known Activations