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. 441
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    No
    0.78
    Der
    0.75
    ::
    0.74
    Expl
    0.74
    Def
    0.73
    :
    0.73
     فه
    0.72
    En
    0.71
    Through
    0.70
    ,
    0.70
    POSITIVE LOGITS
     Palestinian
    1.21
     volleyball
    1.21
     basketball
    1.21
     bitcoin
    1.20
     ransomware
    1.20
     canadian
    1.20
     фонбет
    1.20
     nonprofit
    1.19
     cemetery
    1.19
     motorcycle
    1.18
    Activations Density 8.973%

    No Known Activations