© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2254
    Prev
    Next
    INDEX
    Explanations

    following rules and instructions

    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
     rozm
    2.00
     kelu
    1.91
     unsus
    1.90
    움을
    1.89
     rech
    1.86
     osobe
    1.85
     hozz
    1.82
    움
    1.81
     embol
    1.80
     nga
    1.80
    POSITIVE LOGITS
     ordres
    2.13
    遵守
    2.06
    principles
    2.04
    ied
    2.00
    rules
    2.00
     commandments
    1.98
     normas
    1.98
    norms
    1.97
     règles
    1.97
    нор
    1.96
    Activations Density 0.595%

    No Known Activations