© 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. 13355
    Prev
    Next
    INDEX
    Explanations

    what's going 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_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
    给予
    2.03
    ⁽
    2.02
    承
    2.00
    和其他
    1.98
     amare
    1.96
     пое
    1.93
     страхо
    1.88
     आजीवन
    1.84
     ultimate
    1.84
     иң
    1.81
    POSITIVE LOGITS
     agitated
    2.03
     situa
    1.99
    ecycle
    1.96
     scene
    1.89
     paese
    1.86
     spate
    1.85
     commotion
    1.85
    ૫
    1.84
    仼
    1.83
    救援
    1.82
    Activations Density 0.033%

    No Known Activations