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-65K
    4. 3766
    Prev
    Next
    INDEX
    Explanations

    even though

    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
    也会
    1.22
     également
    1.22
    任意
    1.20
    أي
    1.13
    evil
    1.12
    also
    1.07
     również
    1.07
    뱅
    1.07
     anywhere
    1.07
     butadiene
    1.06
    POSITIVE LOGITS
     though
    2.89
     Though
    2.54
    Though
    2.50
     несмотря
    2.23
    though
    2.16
     tho
    1.81
     якщо
    1.65
    handed
    1.60
    handedly
    1.54
     remotely
    1.48
    Activations Density 0.045%

    No Known Activations