© 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. 66092
    Prev
    Next
    INDEX
    Explanations

    layout, property, xml

    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
     akku
    -1.41
     aussit
    -1.23
     flotte
    -1.23
     mikina
    -1.22
     merke
    -1.20
    INION
    -1.20
     fejl
    -1.20
    AutoModerator
    -1.18
    ların
    -1.17
    踵
    -1.17
    POSITIVE LOGITS
    paravant
    1.16
     with
    1.13
     Bute
    1.09
    itete
    1.09
     vacuna
    1.08
     мужская
    1.06
     чрез
    1.05
     Gato
    1.04
    Татьяна
    1.04
    Наталья
    1.03
    Activations Density 0.004%

    No Known Activations