© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8397
    Prev
    Next
    INDEX
    Explanations

    the phrase "well as"

    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
    টা
    1.00
     আহম্মদ
    0.97
    FormProvider
    0.93
    }:{
    0.88
     Kenyatta
    0.85
    টাও
    0.83
    ymi
    0.83
    Plastic
    0.82
     metavar
    0.82
     معا
    0.82
    POSITIVE LOGITS
    ến
    1.13
     기타
    0.95
     Numerous
    0.85
     as
    0.79
    级
    0.77
    ?!?
    0.76
     copious
    0.75
     jako
    0.74
     inú
    0.74
    ㅎ
    0.73
    Activations Density 0.009%

    No Known Activations