© 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. 127375
    Prev
    Next
    INDEX
    Explanations

    album titles

    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
     for
    -1.45
    얘
    -1.40
     zobac
    -1.38
     the
    -1.25
     what
    -1.23
     Estos
    -1.20
    ходили
    -1.20
     takže
    -1.18
    妡
    -1.16
    čem
    -1.15
    POSITIVE LOGITS
    ]
    1.70
    <h2>
    1.53
    ↵↵↵
    1.43
     then
    1.43
    <h3>
    1.33
     its
    1.32
    Its
    1.32
    ↵↵
    1.30
     efectuar
    1.30
     asesoramiento
    1.29
    Activations Density 0.150%

    No Known Activations