© 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. 11319
    Prev
    Next
    INDEX
    Explanations

    estoy cambiando

    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
    𝘳
    2.62
    𝘭
    2.39
    kin
    2.33
    खास्त
    2.26
    neg
    2.24
    乎
    2.24
    lerde
    2.23
     connot
    2.21
    
    2.21
     vâr
    2.21
    POSITIVE LOGITS
    ি
    3.48
    ي
    3.14
    ی
    3.11
    t
    3.02
    ০
    2.98
    ੀ
    2.97
    s
    2.92
    ీ
    2.90
    ing
    2.85
    ી
    2.81
    Activations Density 0.008%

    No Known Activations