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. 8539
    Prev
    Next
    INDEX
    Explanations

    push_back operation

    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
    titudes
    -0.69
     🤩
    -0.69
    viť
    -0.69
    😍
    -0.67
    titud
    -0.66
    uak
    -0.66
    uyen
    -0.66
    Removal
    -0.66
    Wrapper
    -0.65
    yw
    -0.65
    POSITIVE LOGITS
    push
    2.16
     push
    2.00
     pushing
    1.69
     Push
    1.41
     pushes
    1.41
    PUSH
    1.38
    Pushing
    1.36
     Pushing
    1.31
     pushed
    1.31
    Push
    1.31
    Activations Density 0.003%

    No Known Activations