© 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. 22-GEMMASCOPE-RES-131K
    7. 15520
    Prev
    Next
    INDEX
    Explanations

    adjective noun pairs

    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
    8
    -1.59
    を
    -1.41
    5
    -1.39
    7
    -1.39
     professionelle
    -1.35
    9
    -1.35
     normalen
    -1.34
    4
    -1.34
    などを
    -1.32
    6
    -1.31
    POSITIVE LOGITS
     what
    1.51
     sehr
    1.48
    Before
    1.45
    While
    1.36
    ेमाल
    1.35
    During
    1.34
    Taking
    1.31
    のご紹介
    1.31
    Although
    1.30
    ēju
    1.28
    Activations Density 0.154%

    No Known Activations