© 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. 65777
    Prev
    Next
    INDEX
    Explanations

    and followed by a descriptor

    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
    tieth
    -1.27
     både
    -1.24
     fameux
    -1.17
    を
    -1.16
    aneity
    -1.13
    entown
    -1.11
     ë
    -1.11
    iczne
    -1.09
    foundland
    -1.09
    ológico
    -1.08
    POSITIVE LOGITS
     grasas
    1.09
    の人生
    1.07
     lesiones
    1.06
     secuen
    1.05
     のみ
    1.03
     estadounidense
    1.03
     hagy
    1.02
    拽
    1.02
     Only
    1.02
     In
    1.02
    Activations Density 0.059%

    No Known Activations