© 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. 7914
    Prev
    Next
    INDEX
    Explanations

    database cursor retrieval

    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
     maka
    1.72
     ஆனால்
    1.64
     vállalat
    1.63
     sedangkan
    1.57
     frase
    1.56
    しかし
    1.54
     cosa
    1.54
    것
    1.52
     اما
    1.51
    tidak
    1.51
    POSITIVE LOGITS
     connections
    1.23
     preferences
    1.20
     connection
    1.18
     preferential
    1.17
     protection
    1.16
     protective
    1.15
     relative
    1.14
     detection
    1.12
     connecting
    1.09
     patterned
    1.08
    Activations Density 0.020%

    No Known Activations