© 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. 67926
    Prev
    Next
    INDEX
    Explanations

    such as ; including

    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
     or
    -2.03
     should
    -1.60
    puestas
    -1.55
     enormous
    -1.48
     allow
    -1.45
     any
    -1.45
     anything
    -1.45
     problems
    -1.45
     also
    -1.44
    据说
    -1.44
    POSITIVE LOGITS
    :
    1.59
    玙
    1.45
     poign
    1.42
    kinda
    1.41
     xadrez
    1.37
     «
    1.36
    IPMENT
    1.34
    NCIS
    1.32
     …..
    1.29
    mY
    1.27
    Activations Density 0.097%

    No Known Activations