© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4343
    Prev
    Next
    INDEX
    Explanations

    per ception/ceive/forms/verted

    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_12_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
     prese
    1.56
    ffected
    1.54
    াধীন
    1.54
    remo
    1.51
    bergh
    1.44
    glow
    1.40
    깝
    1.38
     ​​
    1.36
    愎
    1.31
     Idee
    1.30
    POSITIVE LOGITS
    ディション
    2.30
    immon
    2.13
     hole
    2.07
    ực
    2.03
    ipheral
    2.03
     Hole
    2.02
     Canopy
    1.97
     holes
    1.96
     arugula
    1.90
     GTI
    1.89
    Activations Density 0.068%

    No Known Activations