© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 16265
    Prev
    Next
    INDEX
    Explanations

    negative correlation (as one increases, other decreases)

    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_13_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
     proguardFiles
    1.93
     _$_
    1.92
     spacerItem
    1.83
    即便
    1.80
    டும்ப
    1.79
     prothorace
    1.78
     조금
    1.74
    <unused946>
    1.73
    <unused2163>
    1.71
     $(`.
    1.71
    POSITIVE LOGITS
     (
    1.52
    ,
    1.43
     ,
    1.38
    /
    1.34
    ized
    1.34
     er
    1.31
    (
    1.30
    istic
    1.21
    ised
    1.21
    O
    1.19
    Activations Density 0.058%

    No Known Activations