© 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. 12487
    Prev
    Next
    INDEX
    Explanations

    your name, love

    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
    
    1.69
    Wikipedia
    1.65
    ﯼ
    1.63
    Classifier
    1.59
    ֱ
    1.58
    Daemon
    1.58
    Ceylon
    1.58
     :-
    1.54
    مط
    1.53
    יות
    1.52
    POSITIVE LOGITS
     जल्
    1.23
    igan
    1.19
    ipu
    1.19
     house
    1.17
    iga
    1.15
     strategic
    1.14
     mechanism
    1.14
    idental
    1.13
    inu
    1.11
    ins
    1.08
    Activations Density 0.000%

    No Known Activations