© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6571
    Prev
    Next
    INDEX
    Explanations

    US cities and locations

    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
     drowned
    1.74
     Bruck
    1.61
     plowed
    1.59
    躺
    1.59
     Cry
    1.53
     drowning
    1.52
     Weil
    1.50
     plow
    1.49
     Brenner
    1.47
     녹
    1.46
    POSITIVE LOGITS
    ellery
    1.21
     Beaufort
    1.19
     Tourists
    1.13
    izziness
    1.11
    hoo
    1.07
    usin
    1.06
    プレゼント
    1.04
    phed
    1.04
     подар
    1.03
    impul
    1.02
    Activations Density 0.093%

    No Known Activations