© 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. 3576
    Prev
    Next
    INDEX
    Explanations

    systems and policies

    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
    श्य
    1.19
    唧
    1.17
    amientos
    1.13
    ète
    1.10
    ètes
    1.07
    installer
    1.06
    Tooltip
    1.05
    aider
    1.05
    Insider
    1.04
    denum
    1.04
    POSITIVE LOGITS
     tratados
    1.22
    
    1.22
     tratado
    1.22
     paz
    1.20
     차지
    1.20
     cardNumber
    1.19
     andRow
    1.18
     थोरो
    1.18
    IFI
    1.17
     ポー
    1.16
    Activations Density 0.000%

    No Known Activations