© 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. 22-GEMMASCOPE-RES-131K
    7. 33530
    Prev
    Next
    INDEX
    Explanations

    Department of government agencies

    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
     Füßen
    -1.57
    ).
    -1.41
     этих
    -1.35
    ."
    -1.35
     trusty
    -1.30
    தி
    -1.27
     unangemess
    -1.24
     Eigentü
    -1.24
    .”
    -1.23
    gets
    -1.23
    POSITIVE LOGITS
    ’
    1.38
     الحكومة
    1.37
    気に入り
    1.31
    ークル
    1.31
    eneral
    1.27
    peo
    1.26
     Tuner
    1.26
    ଶ
    1.24
    nment
    1.23
     including
    1.22
    Activations Density 0.024%

    No Known Activations