© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3705
    Prev
    Next
    INDEX
    Explanations

    wie... spricht man

    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_10/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
    A
    -2.97
     This
    -2.59
     of
    -2.59
    t
    -2.47
    .'
    -2.28
    此外
    -2.25
    ࿚
    -2.25
    AN
    -2.23
    на
    -2.22
    B
    -2.22
    POSITIVE LOGITS
    橚
    2.69
    说是
    2.38
    狃
    2.27
    蹌
    2.16
     folgt
    2.14
     ideales
    2.11
    饜
    2.11
     respectivos
    2.11
    褔
    2.09
    埽
    2.09
    Activations Density 0.001%

    No Known Activations