© 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. 64278
    Prev
    Next
    INDEX
    Explanations

    player substitutions

    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
     cuando
    -1.29
     when
    -1.26
    Sometimes
    -1.07
     yearly
    -1.06
     berbagai
    -1.05
     actualmente
    -1.05
     όταν
    -1.03
     Когда
    -1.02
     sometimes
    -1.00
    petits
    -0.99
    POSITIVE LOGITS
     instead
    1.42
     replaces
    1.30
     replacing
    1.27
    llllll
    1.25
     replace
    1.24
     substitutes
    1.21
     substituting
    1.20
     substitution
    1.16
     sostitu
    1.15
     remplace
    1.14
    Activations Density 0.010%

    No Known Activations