© 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. 4988
    Prev
    Next
    INDEX
    Explanations

    contrasting clarification

    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
     attempts
    0.98
    attempts
    0.96
    mostly
    0.93
     bann
    0.92
    relatively
    0.91
    fallback
    0.90
    朋
    0.88
     autor
    0.88
     mostly
    0.84
    bans
    0.83
    POSITIVE LOGITS
     necesitamos
    1.16
    Tenemos
    1.08
     Hoy
    1.04
     świę
    1.03
     debemos
    1.02
    Nuestro
    1.02
     Nuestro
    1.00
    荳
    0.99
     miro
    0.98
     zároveň
    0.97
    Activations Density 0.223%

    No Known Activations