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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8244
    Prev
    Next
    INDEX
    Explanations

    picture :

    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
     under
    -0.91
    Under
    -0.76
    wane
    -0.72
    >*
    -0.71
    шти
    -0.70
     drove
    -0.68
    唯一的
    -0.68
     labored
    -0.67
     beobachten
    -0.66
    oblig
    -0.65
    POSITIVE LOGITS
     мем
    0.73
    ulously
    0.71
    prefix
    0.70
     Pineda
    0.66
    ComponentName
    0.66
    ḍ
    0.66
    acão
    0.65
    FACT
    0.64
     prin
    0.63
     lidt
    0.63
    Activations Density 0.052%

    No Known Activations