© 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. 71923
    Prev
    Next
    INDEX
    Explanations

    make way for

    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
     climático
    -2.05
     anden
    -1.83
    tku
    -1.74
     anun
    -1.71
    栊
    -1.68
    together
    -1.66
    ”？
    -1.63
     TICKETS
    -1.63
    猹
    -1.61
    躄
    -1.58
    POSITIVE LOGITS
    。“
    1.66
     Especially
    1.63
    .“
    1.59
    :
    1.58
     Allowing
    1.56
     Of
    1.53
    t
    1.51
     toil
    1.50
     Nowadays
    1.48
    c
    1.48
    Activations Density 0.002%

    No Known Activations