© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109841
    Prev
    Next
    INDEX
    Explanations

    gradient and its uses

    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
    dims
    -0.78
    Semoga
    -0.75
     DISTINCT
    -0.75
     dims
    -0.74
     Transporter
    -0.73
    Unmount
    -0.73
    Clas
    -0.72
     sele
    -0.72
    doj
    -0.71
    Kelebihan
    -0.71
    POSITIVE LOGITS
     stops
    1.30
     gradient
    1.27
    stops
    1.26
     stop
    1.16
     Stops
    1.06
     Stopping
    1.05
     stopping
    1.05
     grad
    1.01
     stopped
    0.99
    gradient
    0.99
    Activations Density 0.008%

    No Known Activations