© 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. 10544
    Prev
    Next
    INDEX
    Explanations

    asking about desired tone or vibe

    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
    ↵
    1.24
    ↵↵
    1.03
     As
    1.01
     راز
    0.97
    ↵↵↵
    0.94
     exclude
    0.88
     Osm
    0.87
    apse
    0.87
    주의
    0.86
    ose
    0.86
    POSITIVE LOGITS
    𒇽
    1.35
    𒌷
    1.30
    Ⴊ
    1.23
    𒌨
    1.23
    𒀝
    1.23
    𒈪
    1.23
    〢
    1.22
    nuevo
    1.22
    ▿
    1.21
    𒂠
    1.21
    Activations Density 0.022%

    No Known Activations