Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9128
    Prev
    Next
    INDEX
    Explanations

    Daydreaming, day off, day out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ʂ
    1.09
    sman
    1.05
    ssh
    1.02
    conexion
    0.99
    বিনোদন
    0.95
     ವೇಳ
    0.95
     depository
    0.94
     doomed
    0.92
    𝐭
    0.91
     raged
    0.90
    POSITIVE LOGITS
    dreams
    1.26
    л
    1.10
     honest
    1.09
    OfWeek
    1.04
     écrit
    0.98
     acreditar
    0.98
     Nase
    0.97
     vile
    0.95
     gak
    0.93
     acred
    0.92
    Activations Density 0.067%

    No Known Activations