© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12611
    Prev
    Next
    INDEX
    Explanations

    academic paper DOIs

    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
    ુ
    1.04
     burung
    1.01
    じゃ
    1.00
    种
    0.97
     شدہ
    0.97
    簍
    0.96
    いますが
    0.96
    種
    0.94
    मुझे
    0.94
    ất
    0.94
    POSITIVE LOGITS
     legisl
    0.98
     co
    0.91
     glor
    0.91
     Particip
    0.89
     athlet
    0.88
    intArray
    0.87
     emble
    0.87
    OCO
    0.86
     refer
    0.86
    CODES
    0.86
    Activations Density 0.059%

    No Known Activations