© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118771
    Prev
    Next
    INDEX
    Explanations

    method calls or object instantiation

    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
     рецепта
    -0.93
    “
    -0.83
    BuildContext
    -0.81
    会不会
    -0.81
    mtu
    -0.79
    These
    -0.78
    "
    -0.78
    how
    -0.77
    地
    -0.77
    tml
    -0.76
    POSITIVE LOGITS
     this
    1.52
     your
    0.99
    prize
    0.98
    远的
    0.93
     my
    0.93
     بيها
    0.92
     our
    0.90
    ﺑ
    0.89
    えている
    0.89
     tuvimos
    0.89
    Activations Density 0.017%

    No Known Activations