© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14805
    Prev
    Next
    INDEX
    Explanations

    tied to following 'to'

    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
     nbfs
    1.82
    esist
    1.72
    ₁,
    1.71
     någon
    1.68
     '*',
    1.68
     पौधों
    1.66
    bats
    1.65
    лён
    1.61
    iał
    1.61
     października
    1.61
    POSITIVE LOGITS
     glory
    1.61
     p
    1.44
     d
    1.43
    ivar
    1.38
     commentary
    1.36
     marvel
    1.32
     lively
    1.31
     wonder
    1.31
     affair
    1.28
     drama
    1.25
    Activations Density 0.172%

    No Known Activations