© 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. 12226
    Prev
    Next
    INDEX
    Explanations

    describing charming, old places

    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
    
    1.01
    Ци
    1.00
    .`);
    0.99
     prospects
    0.98
     columnalign
    0.98
    сход
    0.94
    。<
    0.93
    ₁.
    0.92
    SourceObject
    0.92
    dataloader
    0.91
    POSITIVE LOGITS
     invariable
    1.19
     stupid
    1.16
     sürekli
    1.09
     Rue
    1.08
     constantly
    1.08
     ständig
    1.08
     painstaking
    1.08
     Blvd
    1.07
     patented
    1.06
     oh
    1.05
    Activations Density 0.051%

    No Known Activations