© 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. 34-GEMMASCOPE-RES-131K
    7. 117211
    Prev
    Next
    INDEX
    Explanations

    maintainer type

    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_34/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
    mètres
    -0.81
     ниж
    -0.80
    Chord
    -0.80
    bject
    -0.77
     Chord
    -0.75
     恤
    -0.75
     Bak
    -0.74
     impar
    -0.73
     Dal
    -0.71
     przedsiębior
    -0.70
    POSITIVE LOGITS
     охра
    0.73
    rugated
    0.67
    jusqu
    0.67
    Clever
    0.66
    voici
    0.65
    Automatically
    0.65
     Flexib
    0.65
     thousand
    0.64
    isuke
    0.63
    Дополнитель
    0.62
    Activations Density 0.054%

    No Known Activations