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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9987
    Prev
    Next
    INDEX
    Explanations

    gaze fixed on

    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_13_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
     N
    0.94
    1
    0.90
     mand
    0.90
     S
    0.88
    5
    0.86
     over
    0.85
    6
    0.83
    N
    0.82
     it
    0.82
     ban
    0.82
    POSITIVE LOGITS
    जागरण
    1.24
     inhomogeneities
    1.24
    conceptual
    1.23
    denoted
    1.23
    ğinde
    1.23
    complexity
    1.20
    AssetDiscovery
    1.20
    StarGo
    1.16
    fortunate
    1.16
     Polskiej
    1.15
    Activations Density 0.191%

    No Known Activations