© 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. 13910
    Prev
    Next
    INDEX
    Explanations

    political issues and resource management

    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
     玄関
    -1.25
     ребё
    -1.11
    chnen
    -1.09
     olivat
    -1.06
    ly
    -1.05
     gyven
    -1.05
    ka
    -1.04
     kaum
    -1.03
     inte
    -1.02
     revolu
    -1.02
    POSITIVE LOGITS
     on
    1.68
     from
    1.50
    baikan
    1.26
    abaikan
    1.24
    drá
    1.11
    ahnya
    1.08
     oferty
    1.06
     brukes
    1.05
     empfind
    1.05
     milyen
    1.03
    Activations Density 0.039%

    No Known Activations