© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118739
    Prev
    Next
    INDEX
    Explanations

    version 4 pathway features

    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
     connexe
    -0.81
     Young
    -0.72
    Young
    -0.70
    orp
    -0.67
    ksen
    -0.66
     ce
    -0.66
    tabs
    -0.65
    BRACK
    -0.65
     Path
    -0.64
     tabs
    -0.64
    POSITIVE LOGITS
    🕥
    0.76
    enson
    0.75
     запом
    0.74
    ineas
    0.72
     žel
    0.71
    Mange
    0.70
     sitesinde
    0.70
    Compos
    0.69
     Timmy
    0.69
     Eunice
    0.69
    Activations Density 0.062%

    No Known Activations