© 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. 5364
    Prev
    Next
    INDEX
    Explanations

    read -r -d $'\0'

    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
    itys
    1.31
    ITY
    1.24
    ity
    1.24
    Works
    1.18
    썻
    1.16
    भूति
    1.13
    conductor
    1.12
    '):
    1.11
    OS
    1.11
    instr
    1.11
    POSITIVE LOGITS
     enthusiasm
    1.35
     nonzero
    1.31
    ،
    1.26
     opposing
    1.25
     stumble
    1.24
     этими
    1.23
    而成
    1.22
     жана
    1.21
     आणि
    1.21
     resentment
    1.20
    Activations Density 0.169%

    No Known Activations