© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10552
    Prev
    Next
    INDEX
    Explanations

    Show, Don't Tell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     خام
    1.73
     Gemeinde
    1.66
     단
    1.48
     دان
    1.48
     seni
    1.46
    lein
    1.45
     langs
    1.45
    σμ
    1.42
    na
    1.37
     수익
    1.34
    POSITIVE LOGITS
    <unused1875>
    2.52
    <unused1728>
    2.26
    ⬯
    2.24
     intrusions
    2.24
    <unused2033>
    2.18
     confronted
    2.16
     bombardment
    2.15
    <unused189>
    2.11
     kttt
    2.10
    <unused162>
    2.09
    Activations Density 0.062%

    No Known Activations