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. 7759
    Prev
    Next
    INDEX
    Explanations

    Google

    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
    домо
    -0.82
    ルド
    -0.81
     Ely
    -0.80
    萝
    -0.77
    Ely
    -0.77
    omitempty
    -0.77
    ̄
    -0.76
     La
    -0.76
     IOError
    -0.74
    라마
    -0.74
    POSITIVE LOGITS
    google
    1.09
     Google
    0.99
    Google
    0.93
     google
    0.90
    pulsera
    0.88
    Iglesia
    0.82
     GOOGLE
    0.81
    Día
    0.80
    本田
    0.80
    huawei
    0.79
    Activations Density 0.009%

    No Known Activations