© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10101
    Prev
    Next
    INDEX
    Explanations

    specific words followed by elaboration

    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
     ab
    1.10
     μέρος
    0.94
    ends
    0.91
    ابا
    0.89
     part
    0.88
     a
    0.88
     some
    0.87
    !
    0.85
     ent
    0.84
    托
    0.84
    POSITIVE LOGITS
     açúcar
    1.71
     poplar
    1.68
    โยชน์
    1.68
     projetos
    1.65
    切り
    1.65
    óloga
    1.62
     ም
    1.62
    ഴിക്ക
    1.59
     escolha
    1.57
     realizzazione
    1.57
    Activations Density 0.000%

    No Known Activations