© 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. 8218
    Prev
    Next
    INDEX
    Explanations

    passion for engaging with specific topics

    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
    organised
    1.88
     Organis
    1.76
    ṭ
    1.64
    alling
    1.63
    emons
    1.61
    iss
    1.59
    āt
    1.58
    organisation
    1.57
     Organisation
    1.56
    ş
    1.56
    POSITIVE LOGITS
     Wyoming
    1.65
     WV
    1.58
     Kansas
    1.55
     Lehigh
    1.53
     linebacker
    1.52
     Pennsylvania
    1.50
     Utah
    1.50
     Harrisburg
    1.49
     quarterback
    1.47
     Alabama
    1.46
    Activations Density 0.457%

    No Known Activations