© 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. 3766
    Prev
    Next
    INDEX
    Explanations

    time elapsed since event

    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
    y
    3.33
    에
    3.25
    en
    2.99
    NUMX
    2.98
    aliment
    2.90
    ים
    2.88
    ে
    2.82
    า
    2.79
    ing
    2.79
    aes
    2.76
    POSITIVE LOGITS
    ty
    2.64
    mstyle
    2.56
    mrow
    2.49
    쨰
    2.37
    ın
    2.36
    
    2.32
    miot
    2.31
    ھی
    2.30
    সরকারী
    2.27
    nya
    2.27
    Activations Density 0.021%

    No Known Activations