© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 636
    Prev
    Next
    INDEX
    Explanations

    Google and tech companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    1.00
     related
    0.99
     feat
    0.93
     also
    0.92
     treat
    0.91
     accessory
    0.90
     dose
    0.89
     feature
    0.88
     set
    0.88
     (
    0.88
    POSITIVE LOGITS
    david
    1.76
    daniel
    1.75
    google
    1.72
    facebook
    1.71
    gmail
    1.67
    谷歌
    1.66
    IBM
    1.65
    GOOGLE
    1.63
    apache
    1.61
    Google
    1.61
    Activations Density 0.390%

    No Known Activations