© 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. 101841
    Prev
    Next
    INDEX
    Explanations

    numbers followed by of or +

    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
     paisagem
    -1.75
     variedade
    -1.59
     prostu
    -1.55
     lámpara
    -1.50
     velha
    -1.48
    睥
    -1.45
    了一个
    -1.43
     geração
    -1.40
    tiske
    -1.38
    鸾
    -1.38
    POSITIVE LOGITS
     to
    1.92
    },
    1.84
    with
    1.66
    }
    1.63
    媄
    1.59
    ),
    1.59
     ২০
    1.55
    ،
    1.54
    ؛
    1.53
     を
    1.50
    Activations Density 0.009%

    No Known Activations