© 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. 110558
    Prev
    Next
    INDEX
    Explanations

    we followed by actions

    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
     intentando
    -1.45
     säll
    -1.42
     luchando
    -1.41
     salonu
    -1.38
    }
    -1.34
     their
    -1.34
    "]
    -1.29
    吭
    -1.29
     ganska
    -1.26
    yaç
    -1.26
    POSITIVE LOGITS
     or
    1.19
    ции
    1.13
    embley
    1.12
    roslav
    1.06
    copio
    1.04
     oeil
    1.04
    褄
    1.03
     jezelf
    1.02
     “
    1.02
     enough
    1.02
    Activations Density 0.259%

    No Known Activations