© 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. 223
    Prev
    Next
    INDEX
    Explanations

    android tools namespace

    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
     '
    -1.82
     a
    -1.77
    ">(</
    -1.63
     of
    -1.61
    ."
    -1.60
    𝓎
    -1.56
     considérons
    -1.54
    "].
    -1.52
     minden
    -1.52
    PasswordEncoder
    -1.51
    POSITIVE LOGITS
    There
    2.16
    Some
    1.91
    After
    1.90
    Several
    1.86
    Because
    1.80
    Having
    1.77
    Creating
    1.77
    Another
    1.73
    From
    1.72
    They
    1.71
    Activations Density 0.006%

    No Known Activations