© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221356
    Prev
    Next
    INDEX
    Explanations

    interpersonal communication and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    ennials
    0.42
    alagi
    0.41
     Brokers
    0.39
    控え
    0.39
     multipurpose
    0.39
    ंदी
    0.39
    绽
    0.38
     dog
    0.38
    깽
    0.38
     Engagement
    0.37
    POSITIVE LOGITS
    memory
    0.48
    communic
    0.41
    byt
    0.41
     коммуника
    0.41
     Kommunikation
    0.40
     memory
    0.40
    療法
    0.39
     compara
    0.39
    newpage
    0.39
    tas
    0.38
    Activations Density 0.011%

    No Known Activations