© 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. 34-GEMMASCOPE-RES-131K
    4. 70315
    Prev
    Next
    INDEX
    Explanations

    question and exclamation marks

    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
    怵
    -0.75
    ptt
    -0.74
    ianie
    -0.74
     PATRICK
    -0.73
     ausgewählt
    -0.71
    分に
    -0.68
     prejudice
    -0.67
    ত্ত
    -0.67
     rebel
    -0.66
    IonicModule
    -0.66
    POSITIVE LOGITS
     mark
    2.84
     marks
    2.58
    mark
    2.13
    マーク
    2.08
    marks
    1.95
     Mark
    1.91
     Marks
    1.82
    Mark
    1.81
    MARK
    1.81
     MARK
    1.80
    Activations Density 0.032%

    No Known Activations