© 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. 7-GEMMASCOPE-2-RES-16K
    7. 285
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    वासी
    1.70
    sort
    1.66
     p
    1.61
     viagem
    1.60
     luz
    1.57
    ाना
    1.54
    to
    1.54
    wego
    1.53
    is
    1.51
     viaje
    1.51
    POSITIVE LOGITS
    汹
    2.30
    𝓹
    2.14
    𝓻
    1.99
    𝓶
    1.96
    𝓵
    1.94
    மை
    1.92
    𝓮
    1.91
    蜍
    1.90
     spoiling
    1.90
    ^{[\
    1.89
    Activations Density 0.858%

    No Known Activations