© 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. 3076
    Prev
    Next
    INDEX
    Explanations

    introduces examples

    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
    e
    1.92
    erol
    1.83
    ان
    1.79
    er
    1.78
    o
    1.78
    hong
    1.68
    Bo
    1.67
    Re
    1.66
    enia
    1.65
    yal
    1.61
    POSITIVE LOGITS
    InstrumentedTest
    2.88
    ዴት
    2.73
    <unused1222>
    2.53
     جامع
    2.47
    DEFGHIJKLMNOP
    2.45
    दशी
    2.40
    CycleOffset
    2.38
    <unused508>
    2.38
     finement
    2.32
    درا
    2.32
    Activations Density 0.046%

    No Known Activations