© 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. 8838
    Prev
    Next
    INDEX
    Explanations

    cinematic lighting, highly detailed, photorealistic

    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
    ुलकर
    1.00
    家中
    0.96
    スル
    0.88
     Virtue
    0.84
    ὸς
    0.84
     येते
    0.84
    izmi
    0.83
    ی
    0.82
    EVER
    0.82
    การ
    0.82
    POSITIVE LOGITS
    ulence
    1.75
    ulent
    1.52
    irons
    1.29
    iron
    1.17
    ulant
    1.15
    bread
    1.15
    ulents
    1.15
    ulently
    1.10
     rate
    1.06
    ters
    1.04
    Activations Density 0.057%

    No Known Activations