© 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. 22-GEMMASCOPE-RES-131K
    7. 12300
    Prev
    Next
    INDEX
    Explanations

    which is

    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_22/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
    acate
    -0.95
    簀
    -0.88
    livia
    -0.88
    ູ
    -0.88
    itamos
    -0.86
    sprzed
    -0.85
    ществ
    -0.83
    ventud
    -0.82
    úgó
    -0.82
    Ivo
    -0.81
    POSITIVE LOGITS
     often
    1.05
     most
    0.98
     rely
    0.92
     relies
    0.90
     mostly
    0.88
    はこの
    0.88
     are
    0.87
     reliance
    0.84
     largely
    0.84
    \
    0.82
    Activations Density 0.162%

    No Known Activations