© 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. 14436
    Prev
    Next
    INDEX
    Explanations

    guard down

    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_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
    र्चा
    3.11
     sellest
    2.84
    ordia
    2.81
     computerScore
    2.74
    MenuInflater
    2.74
    聿
    2.73
    <bos>
    2.73
    𝘈
    2.69
     tópico
    2.69
    usele
    2.69
    POSITIVE LOGITS
    ar
    3.65
    ر
    3.65
    er
    3.47
    en
    3.02
    र
    2.82
    ality
    2.73
    ل
    2.69
    ার
    2.66
    st
    2.61
    nement
    2.54
    Activations Density 0.011%

    No Known Activations