© 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. 25786
    Prev
    Next
    INDEX
    Explanations

    specific individuals or people

    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
     miércoles
    -1.23
    acakt
    -1.22
    wyżs
    -1.15
     هذا
    -1.12
     jueves
    -1.10
     Mahomes
    -1.09
     otoño
    -1.07
     viernes
    -1.04
    отно
    -1.04
    医生
    -1.02
    POSITIVE LOGITS
     someone
    1.64
     myself
    1.38
     him
    1.35
     who
    1.27
    ('../../../
    1.26
     смогут
    1.19
     anybody
    1.17
     anyone
    1.17
     coloro
    1.15
     everybody
    1.14
    Activations Density 0.052%

    No Known Activations