© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5622
    Prev
    Next
    INDEX
    Explanations

    early years, current state, initial status

    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
    ,
    0.88
     Bond
    0.88
    ée
    0.85
     deed
    0.83
    .
    0.79
     -
    0.79
    ;
    0.78
     bond
    0.78
     l
    0.77
     Pont
    0.77
    POSITIVE LOGITS
     sebelumnya
    1.64
    Previously
    1.60
     Previously
    1.54
     предыду
    1.41
    Earlier
    1.41
    之前的
    1.40
    以往
    1.40
     previous
    1.38
    従来
    1.38
     Previous
    1.38
    Activations Density 0.284%

    No Known Activations