© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60975
    Prev
    Next
    INDEX
    Explanations

    birth dates or biographical details

    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
    ſſen
    -1.96
     then
    -1.86
     senhora
    -1.73
     cojín
    -1.68
     fieltro
    -1.68
     \
    -1.65
     same
    -1.63
     adhesivo
    -1.57
    dáms
    -1.57
    kig
    -1.55
    POSITIVE LOGITS
    ).
    2.84
    ),
    2.42
    )$
    1.96
    l
    1.95
    }
    1.94
    );
    1.91
    r
    1.91
    phylococcus
    1.84
    c
    1.78
    </h3>
    1.76
    Activations Density 0.004%

    No Known Activations