© 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. 22-GEMMASCOPE-RES-131K
    7. 67496
    Prev
    Next
    INDEX
    Explanations

    extends Origin definition

    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
     brancas
    -1.41
     femininas
    -1.27
    gunakan
    -1.27
     Lainnya
    -1.24
     vermelhas
    -1.23
     with
    -1.23
     alkoh
    -1.20
     ostensibly
    -1.19
     ideen
    -1.17
     cleverly
    -1.15
    POSITIVE LOGITS
    or
    1.17
    om
    1.17
     extremely
    1.13
    ou
    1.09
     magnific
    1.08
    w
    1.08
     joyous
    1.05
    不愿意
    1.05
     exuber
    1.05
     Dinas
    1.05
    Activations Density 0.001%

    No Known Activations