© 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. 31273
    Prev
    Next
    INDEX
    Explanations

    adverbializing adjectives

    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
     Änder
    -0.85
    chtigkeit
    -0.84
    ственными
    -0.84
     Лі
    -0.83
     supuesto
    -0.78
    たしか
    -0.75
     Wszyst
    -0.75
     pequeno
    -0.75
    AndView
    -0.74
    名の
    -0.73
    POSITIVE LOGITS
    ly
    4.66
    ously
    2.77
    LY
    2.75
    ingly
    2.64
    lly
    2.64
    ally
    2.53
    ably
    2.52
    ely
    2.52
    ily
    2.50
    ishly
    2.47
    Activations Density 0.235%

    No Known Activations