© 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. 6678
    Prev
    Next
    INDEX
    Explanations

    left with options

    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
    indi
    0.97
    Obs
    0.89
    ![
    0.88
    flowers
    0.84
    Ol
    0.83
    iloc
    0.82
    ili
    0.82
    ఎ
    0.82
    observ
    0.82
    ifl
    0.81
    POSITIVE LOGITS
     AppCompat
    1.19
     Papua
    1.14
     transitional
    1.11
     BCG
    1.10
     macOS
    1.08
     スタッドレスタイヤ
    1.07
     Buena
    1.06
     JavaBean
    1.06
     生活
    1.05
     hWnd
    1.05
    Activations Density 0.014%

    No Known Activations