© 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. 10-GEMMASCOPE-RES-131K
    7. 44092
    Prev
    Next
    INDEX
    Explanations

    names of companies and software libraries

    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
    ꪔ
    -1.58
    signable
    -1.53
    obut
    -1.41
     FACTORY
    -1.39
     )}
    -1.39
     จ
    -1.39
    lowed
    -1.38
     οὐ
    -1.38
    vail
    -1.38
     VAL
    -1.38
    POSITIVE LOGITS
    1
    1.76
     what
    1.45
     his
    1.40
    3
    1.32
    曾經
    1.25
    他
    1.24
    他的
    1.23
     whom
    1.22
    4
    1.22
    5
    1.20
    Activations Density 0.003%

    No Known Activations