© 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. 66496
    Prev
    Next
    INDEX
    Explanations

    names and titles after lord

    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
    ."
    -2.75
     meistens
    -2.53
     teníamos
    -2.47
    ांकि
    -2.42
    itário
    -2.39
    on
    -2.34
    ڧ
    -2.33
    vantaged
    -2.30
    以上です
    -2.25
    でしたが
    -2.22
    POSITIVE LOGITS
    }
    2.70
    挣
    2.47
    aimeJ
    2.47
    </i>
    2.45
    )」
    2.44
    ا
    2.42
    能在
    2.42
    ت
    2.34
    ור
    2.33
    '
    2.31
    Activations Density 0.005%

    No Known Activations