Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7809
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and structure

    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
     }</
    -1.07
    criptures
    -1.05
    雒
    -1.02
    bureau
    -1.01
     anklicken
    -1.00
    lants
    -1.00
    )',
    -1.00
    缮
    -0.99
    )">
    -0.99
     objectForKey
    -0.98
    POSITIVE LOGITS
    ";
    1.11
    \_
    1.08
    _{
    1.07
    _
    1.06
    ")
    1.05
     besonders
    1.01
    ");
    0.99
    ",
    0.98
    Для
    0.98
     даже
    0.97
    Activations Density 0.086%

    No Known Activations