© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 871
    Prev
    Next
    INDEX
    Explanations

    3 colors

    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_65k_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
    inten
    1.66
    uff
    1.51
    wq
    1.49
    int
    1.48
    pp
    1.45
     Idiot
    1.43
    pj
    1.42
    ੌ
    1.42
    braska
    1.38
    Gas
    1.36
    POSITIVE LOGITS
     גבוה
    1.75
    ణులు
    1.54
    较高的
    1.53
     paramount
    1.51
     handicrafts
    1.46
     biotechnology
    1.45
     зарубе
    1.42
     높은
    1.42
     pagoda
    1.40
    нэт
    1.39
    Activations Density 0.000%

    No Known Activations