© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    YYYY-MM-DD dates

    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
    (
    1.64
    H
    1.23
    (|
    1.23
    max
    1.22
     (
    1.22
    )(
    1.12
    )
    1.08
     (~
    1.07
     H
    1.05
    oz
    1.04
    POSITIVE LOGITS
     regener
    1.94
     Timberlake
    1.93
     господар
    1.87
    regener
    1.87
     tapi
    1.86
     regenerate
    1.85
    сама
    1.83
     KPSS
    1.81
     odkazy
    1.80
     поку
    1.80
    Activations Density 0.016%

    No Known Activations