© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 818
    Prev
    Next
    INDEX
    Explanations

    choosing the proper option

    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_65k_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
     Loch
    0.79
     Twitch
    0.75
     Praxis
    0.74
     -
    0.73
     Wals
    0.71
     –
    0.70
    Messaging
    0.70
    …
    0.69
     shamb
    0.69
     failings
    0.66
    POSITIVE LOGITS
     equipments
    1.60
     evidences
    1.50
     drawed
    1.45
     squre
    1.40
     advices
    1.40
     softwares
    1.35
     stuffs
    1.33
     deduced
    1.33
     recommand
    1.32
     logics
    1.31
    Activations Density 0.252%

    No Known Activations