© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8916
    Prev
    Next
    INDEX
    Explanations

    links with ai

    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_22_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
    弛
    0.87
    ery
    0.82
     ڈیٹ
    0.80
    ет
    0.80
    еты
    0.79
     JAN
    0.79
    Levi
    0.78
    jeća
    0.78
    ervi
    0.76
    izzare
    0.76
    POSITIVE LOGITS
     Interpol
    0.88
     সন্ত্রাসী
    0.87
     kültür
    0.87
    留
    0.85
     hybrid
    0.84
    ായിക
    0.82
    balancing
    0.82
     distiller
    0.82
     সন্ত্রাস
    0.80
     safeguards
    0.80
    Activations Density 0.094%

    No Known Activations