© 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. 57521
    Prev
    Next
    INDEX
    Explanations

    /

    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
    "
    -2.19
    }$
    -1.83
     "
    -1.79
     
    -1.67
    一时间
    -1.66
    ("
    -1.63
    想了想
    -1.63
     terminó
    -1.60
     vivía
    -1.60
    ).
    -1.53
    POSITIVE LOGITS
     of
    2.00
    années
    1.72
    angkap
    1.59
     汤
    1.59
    mbH
    1.49
     ませ
    1.47
     pinggang
    1.43
     Warenkorb
    1.42
    mvh
    1.41
    bibit
    1.41
    Activations Density 0.004%

    No Known Activations