© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11089
    Prev
    Next
    INDEX
    Explanations

    SqlDataReader usage

    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
     ples
    2.57
     collocation
    2.40
    जीशन
    2.26
     specification
    2.26
    য়াদ
    2.24
    듑
    2.24
    бора
    2.24
    々
    2.19
    ⼊
    2.16
     środ
    2.13
    POSITIVE LOGITS
    s
    4.52
    sab
    3.21
    sap
    3.16
    ת
    3.15
    ات
    3.08
    ्ले
    2.99
    ska
    2.93
    sj
    2.92
    sma
    2.84
    spr
    2.76
    Activations Density 0.021%

    No Known Activations