© 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. 4345
    Prev
    Next
    INDEX
    Explanations

    fast-paced

    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
    ambil
    2.18
     tanggung
    2.07
    onal
    2.03
     redund
    2.00
    adece
    2.00
     perten
    1.99
    資
    1.98
    isot
    1.95
    았
    1.95
    negl
    1.93
    POSITIVE LOGITS
    idious
    2.29
     chóng
    2.05
     turnaround
    1.90
    脚步
    1.85
    ائد
    1.82
    /////////////
    1.73
    踵
    1.62
     سریع
    1.61
    直線
    1.60
    ANEOUS
    1.59
    Activations Density 0.176%

    No Known Activations