© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26937
    Prev
    Next
    INDEX
    Explanations

    possessive contractions

    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
    んですか
    -1.17
     horrend
    -1.14
    んでしょう
    -1.06
    のですか
    -1.00
     åren
    -1.00
    のだろうか
    -1.00
     Lorsque
    -0.99
     såsom
    -0.95
    itaji
    -0.94
     wciąż
    -0.94
    POSITIVE LOGITS
     relato
    1.09
     then
    1.02
     recomendable
    1.01
     by
    0.99
     descrit
    0.98
     materias
    0.95
    octet
    0.94
    +}\
    0.94
     story
    0.93
    /*:
    0.91
    Activations Density 0.032%

    No Known Activations