© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25039
    Prev
    Next
    INDEX
    Explanations

    no, not, never, without

    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
    Negative Logits
    𓆏
    -1.23
     nogle
    -1.18
     mulighed
    -1.11
     možnost
    -1.10
     voren
    -1.05
     alebo
    -1.03
     ogrom
    -1.02
    INDOW
    -1.02
     полиции
    -1.02
    paket
    -1.01
    POSITIVE LOGITS
     this
    1.31
     even
    1.10
    亟
    1.04
     include
    1.02
     need
    0.98
     particularly
    0.95
    (":
    0.95
    even
    0.95
     require
    0.94
    さらに
    0.94
    Activations Density 0.052%

    No Known Activations