© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15664
    Prev
    Next
    INDEX
    Explanations

    mother, parent, mums, dad

    np_acts-logits-general · gemini-2.5-flash-lite

    mother and parent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dovrà
    0.63
    يق
    0.61
     života
    0.60
    리
    0.59
     дзяржа
    0.59
    ７
    0.59
    ພວກເຮົາ
    0.58
    يح
    0.58
     observar
    0.58
    ８
    0.58
    POSITIVE LOGITS
     Father
    0.92
    father
    0.89
     Parental
    0.88
     parental
    0.88
     fathers
    0.85
     Fathers
    0.84
     father
    0.83
     Mother
    0.83
    fathers
    0.81
     Parent
    0.80
    Activations Density 0.333%

    No Known Activations