© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12200
    Prev
    Next
    INDEX
    Explanations

    walks into a bar

    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_7_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
    1.35
    9
    1.33
    ္
    1.32
    8
    1.32
    final
    1.31
    ﾂ
    1.29
    self
    1.29
    ting
    1.28
    ization
    1.26
    6
    1.25
    POSITIVE LOGITS
     ngựa
    1.86
     pública
    1.85
     reparar
    1.81
     élargies
    1.80
     ampli
    1.79
     Bremen
    1.77
    präsident
    1.76
     vectơ
    1.76
     irgende
    1.74
     겁
    1.74
    Activations Density 0.084%

    No Known Activations