© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7295
    Prev
    Next
    INDEX
    Explanations

    obtain one

    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
    fortunes
    -2.25
    渽
    -2.23
     of
    -2.16
     you
    -2.02
    尐
    -1.94
    푣
    -1.89
    けれ
    -1.88
     across
    -1.86
     "")
    -1.85
     obtained
    -1.82
    POSITIVE LOGITS
    ers
    2.59
     obtain
    2.30
    e
    2.19
     comuns
    2.17
    ఙ
    2.14
    {
    2.13
     zijn
    2.13
     perdido
    2.08
    ]
    2.08
     a
    2.06
    Activations Density 0.017%

    No Known Activations