© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8998
    Prev
    Next
    INDEX
    Explanations

    are a/an/given/to/you

    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_22_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
    ⑴
    1.02
    льд
    0.95
    ①
    0.87
    に関
    0.87
    φ
    0.86
     ตำ
    0.85
    слови
    0.83
     ①
    0.83
    ⑶
    0.82
    ⒈
    0.81
    POSITIVE LOGITS
     gebaut
    0.99
     hela
    0.98
     Gobern
    0.97
     bouw
    0.97
     bauen
    0.95
    朝着
    0.95
     pinn
    0.93
     Reforma
    0.93
     membangun
    0.92
     vyt
    0.92
    Activations Density 0.041%

    No Known Activations