© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6794
    Prev
    Next
    INDEX
    Explanations

    recipe ingredients and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    frag
    1.56
    
    1.52
    Eugene
    1.45
    Hb
    1.45
    EF
    1.38
    PON
    1.37
     unavoid
    1.37
     congen
    1.37
     OU
    1.36
    HOM
    1.36
    POSITIVE LOGITS
     row
    1.26
    ี่ยง
    1.14
     crate
    1.04
    绉
    1.04
     VCS
    1.02
     chaining
    1.02
    кономи
    1.02
     rows
    1.01
     Row
    0.98
    țit
    0.94
    Activations Density 0.011%

    No Known Activations