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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7694
    Prev
    Next
    INDEX
    Explanations

    actions to something

    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
    hasRole
    -1.05
     besitzen
    -1.02
    gegangen
    -0.96
    采用了
    -0.94
     hybride
    -0.90
     poë
    -0.90
    pse
    -0.89
    laa
    -0.88
     financier
    -0.88
    れています
    -0.88
    POSITIVE LOGITS
     ensure
    2.92
     help
    2.59
     avoid
    2.28
     enable
    2.16
     make
    2.13
     get
    2.08
     allow
    2.05
     give
    1.88
     keep
    1.86
    ensure
    1.82
    Activations Density 0.158%

    No Known Activations