© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 242
    Prev
    Next
    INDEX
    Explanations

    score points or rank

    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
    t
    -2.13
    藹
    -1.79
     titulado
    -1.70
     большим
    -1.70
    dled
    -1.62
     funkce
    -1.60
    "};
    -1.58
     With
    -1.58
    ᎒
    -1.56
    Its
    -1.55
    POSITIVE LOGITS
    up
    1.81
    "
    1.80
    礴
    1.71
     lác
    1.66
    ться
    1.66
     sés
    1.65
    ycznie
    1.62
     emballage
    1.61
    咵
    1.60
     also
    1.59
    Activations Density 0.010%

    No Known Activations