© 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. 34-GEMMASCOPE-RES-131K
    7. 90071
    Prev
    Next
    INDEX
    Explanations

    forms and transitions

    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_34/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
    minimum
    -0.81
    gevens
    -0.79
     Minimum
    -0.77
    oky
    -0.77
     bør
    -0.75
     journaling
    -0.75
     releases
    -0.75
    ˨
    -0.74
     inocente
    -0.74
    Minimum
    -0.73
    POSITIVE LOGITS
     Form
    0.85
    Form
    0.79
     Transitions
    0.78
    떤
    0.75
     transition
    0.73
    ҙ
    0.71
    Chars
    0.69
     హ
    0.68
     transitory
    0.68
    <0x00>
    0.68
    Activations Density 0.029%

    No Known Activations