© 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. 73703
    Prev
    Next
    INDEX
    Explanations

    names and places followed by context

    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
     "
    -2.20
    </h1>
    -2.17
    en
    -1.95
     is
    -1.81
     -
    -1.74
    あります
    -1.71
    To
    -1.71
     crisp
    -1.68
     """
    -1.68
    по
    -1.67
    POSITIVE LOGITS
    </em>
    2.38
     selben
    2.23
    seamnă
    2.08
     necessità
    1.93
     モード
    1.86
    鞮
    1.85
     gelesen
    1.84
     condominio
    1.83
     deiner
    1.82
     ペア
    1.80
    Activations Density 0.005%

    No Known Activations