© 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. 70755
    Prev
    Next
    INDEX
    Explanations

    details

    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
     all
    -1.68
     would
    -1.64
     or
    -1.55
     get
    -1.51
     always
    -1.49
     of
    -1.48
    },
    -1.43
     assist
    -1.39
     as
    -1.39
    <strong>
    -1.37
    POSITIVE LOGITS
    Ꮀ
    1.48
     araba
    1.47
     agir
    1.47
    方で
    1.45
    ൧
    1.45
     fotografie
    1.44
    蕖
    1.39
    sprach
    1.39
     gamla
    1.38
     bébé
    1.38
    Activations Density 0.077%

    No Known Activations