© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 65230
    Prev
    Next
    INDEX
    Explanations

    ancestors and grandparents

    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_31_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
    Famil
    0.45
    Ob
    0.44
    Sibling
    0.42
    amiliar
    0.41
    治
    0.41
    덧
    0.40
    famil
    0.40
     прия
    0.39
     ቤ
    0.39
    s
    0.39
    POSITIVE LOGITS
     ancestors
    0.96
     ancestor
    0.89
     grandpa
    0.79
     grandparent
    0.79
     grandparents
    0.78
     Ancest
    0.77
     ancest
    0.68
     Grandpa
    0.66
     Grandma
    0.66
     grandma
    0.65
    Activations Density 0.033%

    No Known Activations