© 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. 43746
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     its
    -1.89
     today
    -1.66
     the
    -1.58
    ついで
    -1.52
     these
    -1.47
     yesterday
    -1.43
     how
    -1.43
     they
    -1.41
    aujourd
    -1.41
     their
    -1.40
    POSITIVE LOGITS
    ofday
    1.61
    lovakia
    1.49
     Apparently
    1.48
    1
    1.45
    section
    1.35
    2
    1.34
    <bos>
    1.34
    ználat
    1.33
    That
    1.30
    }
    1.28
    Activations Density 0.063%

    No Known Activations