© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39239
    Prev
    Next
    INDEX
    Explanations

    auxiliary + verb

    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
     juſ
    -1.49
    ྄
    -1.48
     ܙ
    -1.46
    actéristi
    -1.45
    敺
    -1.45
    𖣔
    -1.34
    蠃
    -1.32
     llavero
    -1.29
    presumably
    -1.27
    蒌
    -1.27
    POSITIVE LOGITS
     there
    1.31
    There
    1.27
    そのため
    1.24
    there
    1.22
    zło
    1.15
     藍
    1.08
     席
    1.07
    In
    1.07
     exquisitely
    1.07
     dazzling
    1.06
    Activations Density 0.104%

    No Known Activations