© 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. 101089
    Prev
    Next
    INDEX
    Explanations

    Otter, atra, Sumatra, ATR

    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
    '
    -2.91
    櫚
    -2.88
    饪
    -2.88
            
    -2.67
    it
    -2.61
    }
    -2.39
     \&
    -2.36
    |'
    -2.34
    </em>
    -2.17
    珰
    -2.16
    POSITIVE LOGITS
    噥
    2.61
     όταν
    2.39
     caseros
    2.27
    atra
    2.25
     aqueles
    2.23
     行っ
    2.14
    咴
    2.14
    懨
    2.11
     spanning
    2.08
     maakt
    2.02
    Activations Density 0.003%

    No Known Activations