© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    shell or though

    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
    تج
    2.68
    𝔂
    2.51
    ت
    2.50
    E
    2.35
    CK
    2.34
    \\\
    2.33
    EO
    2.33
    ING
    2.30
    STOR
    2.24
    CAC
    2.22
    POSITIVE LOGITS
    ности
    3.31
    اً
    3.04
    зі
    2.85
    
    2.81
    zj
    2.75
    াৰ
    2.74
    াদ
    2.68
    lı
    2.64
    скія
    2.63
    古屋
    2.57
    Activations Density 0.803%

    No Known Activations