© 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. 740
    Prev
    Next
    INDEX
    Explanations

    conversations, teamwork, relationships

    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
     *
    0.73
     Containing
    0.69
     for
    0.69
     if
    0.66
     <=
    0.65
    Generalized
    0.65
     B
    0.64
     ito
    0.64
     /
    0.64
     For
    0.64
    POSITIVE LOGITS
     общения
    1.51
     conversations
    1.46
     camaraderie
    1.34
     mentors
    1.32
     людей
    1.29
     людьми
    1.29
     семья
    1.28
     conversaciones
    1.25
     tirelessly
    1.25
    ⼈
    1.25
    Activations Density 0.273%

    No Known Activations