© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111774
    Prev
    Next
    INDEX
    Explanations

    academic achievement and performance

    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
    紲
    -1.70
    ᜀ
    -1.52
     botas
    -1.48
    intes
    -1.46
    秾
    -1.45
     terraza
    -1.45
     alia
    -1.44
    鶿
    -1.44
     candidat
    -1.44
     mondial
    -1.42
    POSITIVE LOGITS
     on
    1.59
     avviene
    1.48
    4
    1.41
     in
    1.37
     without
    1.32
     under
    1.31
     already
    1.24
    )
    1.22
    ımda
    1.22
    photographe
    1.20
    Activations Density 0.042%

    No Known Activations